Failure-First Embodied AI
By Failure-First Embodied AI
Listen to a podcast, please open Podcast Republic app. Available on Google Play Store and Apple App Store.
Image by Failure-First Embodied AI
Category: Technology
Open in Apple Podcasts
Open RSS feed
Open Website
Rate for this podcast
Subscribers: 0
Reviews: 0
Episodes: 701
Description
Research audio from Failure-First: adversarial evaluation of embodied AI, jailbreak archaeology, policy analysis, and daily paper summaries from the AI safety frontier.
| Episode | Date |
|---|---|
|
[Daily Paper] Hidden in Plain Sight: Diffusion-Based Unrestricted Robotic Attacks on Vision-Language-Action Models
|
Oct 21, 2026 |
|
[Daily Paper] Toward Robust LiDAR Semantic Segmentation for Real-World Deployment: Evaluation under Coarse Labels, Adverse Conditions, and Domain Shifts
|
Oct 19, 2026 |
|
[Daily Paper] SOAR: Source-Aware Reinforcement Learning with Precise Credit Assignment for Search Agents
|
Oct 18, 2026 |
|
[Daily Paper] PRIMS: Physics-guided Representation for Fluid Identification in Multimodal Sensing
|
Sep 22, 2026 |
|
[Daily Paper] FORGE-plus: Force-Budgeted Recovery for Contact-Rich Assembly with a Frozen LLM Supervisor
|
Sep 21, 2026 |
|
[Daily Paper] URF: A Unified Robot Control-Policy Framework for Stable Contact Aware Manipulation
|
Sep 20, 2026 |
|
[Daily Paper] Multimodal Adaptive Control for Safe Robotic Craniotomy Under Partial Observability
|
Sep 19, 2026 |
|
[Daily Paper] DocOps: A Verifiable Benchmark for Autonomous Agents in Complex Document Operations
|
Sep 18, 2026 |
|
[Daily Paper] ReferTrack: Referring Then Tracking for Embodied Visual Tracking
|
Sep 17, 2026 |
|
[Daily Paper] Clinical Pathways as Safety Specifications for Physical AI in Hospital Wards
|
Sep 16, 2026 |
|
[Daily Paper] EgoRecovery: Acquiring Failure Recovery Ability Through Human Recovery Demonstration
|
Sep 15, 2026 |
|
[Daily Paper] The safety failures we are not instrumenting: a perspective on hidden safety-critical challenges in modern AI systems
|
Sep 14, 2026 |
|
[Daily Paper] Agents in the Wild: Where Research Meets Deployment
|
Sep 13, 2026 |
|
[Daily Paper] StratMamba: Strategic and Reactive Stream Partitioning for Path-Efficient LiDAR-Based Obstacle Avoidance
|
Sep 04, 2026 |
|
[Daily Paper] MAMMOTH: A Multi-Modal End-to-End Policy for Off-Road Mobility Robust to Missing Modality
|
Sep 03, 2026 |
|
[Daily Paper] Directional Constraints for Efficient Exploration in Safe Reinforcement Learning
|
Sep 02, 2026 |
|
[Daily Paper] Robust bipedal locomotion on flowable slopes via foot-driven terrain manipulation
|
Sep 01, 2026 |
|
[Daily Paper] Casting Everything to Online API Services? A Survey of Integrating Localized Speech Recognition Models in Robotic Systems
|
Aug 31, 2026 |
|
[Daily Paper] ERR@HRI 3.0 Challenge: Multimodal Detection of Errors and Anticipation in Human-Robot Interactions
|
Aug 30, 2026 |
|
[Daily Paper] Artificial Foveated Perception for Mitigating Shortcut Learning in Robotic Foundation Models
|
Aug 29, 2026 |
|
[Daily Paper] Multimodal Reward Hacking in Reinforcement Learning
|
Aug 28, 2026 |
|
[Daily Paper] FlowDAgger: Human-in-the-Loop Adaptation of Generative Robot Policies in Latent Space
|
Aug 27, 2026 |
|
[Daily Paper] Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agents
|
Aug 26, 2026 |
|
[Daily Paper] Shift & Drift: A Zero-Shot Benchmark for Generalizable and Robust Autonomous Driving Motion Planning
|
Aug 25, 2026 |
|
[Daily Paper] Safe Reinforcement Learning using Ideas from Model Predictive Control
|
Aug 24, 2026 |
|
[Daily Paper] Behavior Foundations for Quadruped Robots: ABot-C0 Technical Report
|
Aug 23, 2026 |
|
[Daily Paper] GraspIT: A Dataset Bridging the Sim-to-Real gap and back for Validated Grasping SE(3) Pose Generation
|
Aug 22, 2026 |
|
[Daily Paper] Synthetic-to-Real Translation for Class-Agnostic Motion Prediction
|
Aug 21, 2026 |
|
[Daily Paper] HoloCount: A Holistic Visual Counting Benchmark for MLLMs
|
Aug 20, 2026 |
|
[Daily Paper] Pluralis v0.1: Towards a Multicultural, Multimodal, Multilingual Benchmark for AI Risk and Reliability
|
Aug 19, 2026 |
|
[Daily Paper] Localized LoRA-MoE: Block-wise Low-Rank Experts With Adaptive Routing
|
Aug 18, 2026 |
|
[Daily Paper] Towards Robustness against Typographic Attack with Training-free Concept Localization
|
Aug 10, 2026 |
|
[Daily Paper] FAR: Failure-Aware Retry for Test-Time Recovery and Continual Policy Improvement
|
Aug 09, 2026 |
|
[Daily Paper] Distributed Multi Robot Lunar Cargo Transportation via Phase Decomposed Reinforcement Learning
|
Aug 08, 2026 |
|
[Daily Paper] LeCropFollow: Latent Space Planning for Navigation in Unstructured Crop Fields
|
Aug 07, 2026 |
|
[Daily Paper] ASPIRE: Agentic /Skills Discovery for Robotics
|
Aug 06, 2026 |
|
[Daily Paper] How Reliable Is Your Jailbreak Judge? Calibration and Adversarial Robustness of Automated ASR Scoring
|
Aug 05, 2026 |
|
[Daily Paper] IHDec: Divergence-Steered Contrastive Decoding for Securing Multi-Turn Instruction Hierarchies
|
Aug 04, 2026 |
|
[Daily Paper] Event-VLA: Action-Conditioned Event Fusion for Robust Vision-Language-Action Model
|
Aug 03, 2026 |
|
[Daily Paper] ActiveVital: Geometry-Aware Embodied Vital Signs Monitoring for Home Healthcare Robots
|
Aug 02, 2026 |
|
[Daily Paper] When Stopping Fails: Rethinking Minimal Risk Conditions through Human-Interactive Autonomous Driving for Safe Transportation Systems
|
Aug 01, 2026 |
|
[Daily Paper] RS-Diffuser: Risk-Sensitive Diffusion Planning with Distributional Value Guidance
|
Jul 31, 2026 |
|
[Daily Paper] Yuvion LLM: An Adversarially-Aware Large Language Model for Content And AI Safety
|
Jul 30, 2026 |
|
[Daily Paper] NavIsaacLab: Generating Realistic Crowd via Parallel Robot Learning for Benchmarking Human-aware Navigation
|
Jul 29, 2026 |
|
[Daily Paper] ForesightSafety-VLA: A Unified Diagnostic Safety Benchmark for Vision-Language-Action Models
|
Jul 28, 2026 |
|
[Daily Paper] Advancing Omnimodal Embodied Agents from Isolated Skills to Everyday Physical Autonomy
|
Jul 27, 2026 |
|
[Daily Paper] Bridging Performance and Generalization in Reinforcement Learning for Agile Flight
|
Jul 26, 2026 |
|
[Daily Paper] Toward Low-Latency Vision-Language Models with Doubly-Correct Predictions in Egocentric Visual Understanding
|
Jul 25, 2026 |
|
[Daily Paper] MIL-LC: A Robust Magnetometer-Inertial-LiDAR Fusion Multimodal Localization Framework
|
Jul 24, 2026 |
|
[Daily Paper] MedGuards: Multi-Agent System for Reliable Medical Error Detection and Correction
|
Jul 23, 2026 |
|
[Daily Paper] SAGE-Nav: Leveraging LLM Planning and Alignment Fusion for Hierarchical Scene Graph-Guided Navigation
|
Jul 22, 2026 |
|
[Daily Paper] Y-BotFrame: An Extensible Embodied Agent Framework for Quadruped Robot Assistants
|
Jul 21, 2026 |
|
[Video] [Daily Paper] Decentralized Pose Graph Riemannian Optimization for Object-based Multi-Robot SLAM
|
Jul 20, 2026 |
|
[Daily Paper] Decentralized Pose Graph Riemannian Optimization for Object-based Multi-Robot SLAM
|
Jul 20, 2026 |
|
[Daily Paper] HoloAgent-0: A Unified Embodied Agent Framework with 3D Spatial Memory
|
Jul 19, 2026 |
|
[Video] [Daily Paper] Flatness Preserves Instruction Following in Vision-Language-Action Models
|
Jul 18, 2026 |
|
[Daily Paper] Flatness Preserves Instruction Following in Vision-Language-Action Models
|
Jul 18, 2026 |
|
[Daily Paper] LIBERO-Safety: A Comprehensive Benchmark for Physical and Semantic Safety in Vision-Language-Action Models
|
Jul 17, 2026 |
|
[Video] [Daily Paper] RoboProcessBench: Benchmarking Process-Aware Understanding in Vision-Language Robotic Manipulation
|
Jul 16, 2026 |
|
[Daily Paper] RoboProcessBench: Benchmarking Process-Aware Understanding in Vision-Language Robotic Manipulation
|
Jul 16, 2026 |
|
[Video] [Daily Paper] No Hidden Prompts Needed! You Can Game AI Peer Review with Presentation-Only Revisions
|
Jul 15, 2026 |
|
[Daily Paper] No Hidden Prompts Needed! You Can Game AI Peer Review with Presentation-Only Revisions
|
Jul 15, 2026 |
|
[Daily Paper] Stubborn: A Streamlined and Unified Reinforcement Learning Framework for Robust Motion Tracking and Fall Recovery for Humanoids
|
Jul 14, 2026 |
|
[Video] [Daily Paper] GEN-Guard: Correcting Generalization Failures for Deployable Federated Surgical AI
|
Jul 13, 2026 |
|
[Daily Paper] GEN-Guard: Correcting Generalization Failures for Deployable Federated Surgical AI
|
Jul 13, 2026 |
|
[Video] [Daily Paper] Fail-RAG : A Retrieval Augmented Generation Informed Framework for Robot Failure Identification
|
Jul 12, 2026 |
|
[Daily Paper] Fail-RAG : A Retrieval Augmented Generation Informed Framework for Robot Failure Identification
|
Jul 12, 2026 |
|
[Video] [Daily Paper] Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models
|
Jul 11, 2026 |
|
[Daily Paper] Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models
|
Jul 11, 2026 |
|
[Video] [Daily Paper] Agentic AI-based Framework for Mitigating Premature Diagnostic Handoff and Silent Hallucination in Healthcare Applications
|
Jul 10, 2026 |
|
[Daily Paper] Agentic AI-based Framework for Mitigating Premature Diagnostic Handoff and Silent Hallucination in Healthcare Applications
|
Jul 10, 2026 |
|
[Video] [Daily Paper] GASE: Gaussian Splatting-Based Automated System for Reconstructing Embodied-Simulation Environments
|
Jul 09, 2026 |
|
[Daily Paper] GASE: Gaussian Splatting-Based Automated System for Reconstructing Embodied-Simulation Environments
|
Jul 09, 2026 |
|
[Video] [Daily Paper] Contactless Respiratory Monitoring on Heterogeneous Mobile Robots: A Multimodal Edge-Computing Framework
|
Jul 08, 2026 |
|
[Daily Paper] Contactless Respiratory Monitoring on Heterogeneous Mobile Robots: A Multimodal Edge-Computing Framework
|
Jul 08, 2026 |
|
[Daily Paper] ActiveSAM: Image-Conditional Class Pruning for Fast and Accurate Open-Vocabulary Segmentation
|
Jul 07, 2026 |
|
[Daily Paper] Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation
|
Jul 06, 2026 |
|
[Daily Paper] Semantic Flip: Synthetic OOD Generation for Robust Refusal in Embodied Question Answering and Spatial Localization
|
Jul 04, 2026 |
|
[Daily Paper] Guided Diffusion with Distilled Vision-Language Reliability for Aerial Navigation
|
Jul 03, 2026 |
|
[Daily Paper] VISTA: Scale-Aware Visual Navigation via Action History Conditioning
|
Jul 02, 2026 |
|
[Daily Paper] From Shield to Target: Denial-of-Service Attacks on LLM-Based Agent Guardrails
|
Jul 01, 2026 |
|
[Daily Paper] PhysVLA: Towards Physically-Grounded VLA for Embodied Robotic Manipulation
|
Jun 30, 2026 |
|
[Daily Paper] Multi-Agent Embodied Autonomous Driving: From V2X Information Exchange to Shared World Models
|
Jun 29, 2026 |
|
[Video] [Daily Paper] SABER: A Stealthy Agentic Black-Box Attack Framework for Vision-Language-Action Models
|
Jun 28, 2026 |
|
[Daily Paper] SABER: A Stealthy Agentic Black-Box Attack Framework for Vision-Language-Action Models
|
Jun 28, 2026 |
|
[Video] [Daily Paper] Strategize Globally, Adapt Locally: A Multi-Turn Red Teaming Agent with Dual-Level Learning
|
Jun 27, 2026 |
|
[Daily Paper] Strategize Globally, Adapt Locally: A Multi-Turn Red Teaming Agent with Dual-Level Learning
|
Jun 27, 2026 |
|
[Daily Paper] Action ControlNet: A Lightweight Delay-Aware Adapter for Smooth Asynchronous Control in Vision-Language-Action Models
|
Jun 26, 2026 |
|
[Video] [Daily Paper] Silent Failures in Physical AI: A Literature Review of Runtime Action Authorization for Autonomous Systems
|
Jun 25, 2026 |
|
[Daily Paper] Silent Failures in Physical AI: A Literature Review of Runtime Action Authorization for Autonomous Systems
|
Jun 25, 2026 |
|
[Report] The National AI Plan's Physical-Action Blind Spot: Why Australia's AI Safety Architecture Stops at the Screen
|
Jun 24, 2026 |
|
[Daily Paper] A Watermark for Vision-Language-Action and World Action Models
|
Jun 24, 2026 |
|
[Daily Paper] Measuring and Mitigating Over-Alignment for LLMs in Multilingual Criminal Law Courts
|
Jun 23, 2026 |
|
[Daily Paper] DEFENGRAPH: Knowledge Graph-Enhanced LLMs for Blue Team Cyber Defense
|
Jun 22, 2026 |
|
[Daily Paper] AOHP: An Open-Source OS-Level Agent Harness for Personalized, Efficient and Secure Interactions
|
Jun 21, 2026 |
|
[Daily Paper] Learning of Robot Safety Policies via Adversarial Synthetic Scenarios
|
Jun 20, 2026 |
|
[Daily Paper] TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate
|
Jun 20, 2026 |
|
[Daily Paper] Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity?
|
Jun 19, 2026 |
|
[Daily Paper] Black-Box Forensics for Conversational LLM Agents
|
Jun 18, 2026 |
|
[Daily Paper] Safe to Check, Unsafe to Use: Relinking at the Compression Boundary of LLM Agents
|
Jun 17, 2026 |
|
[Daily Paper] Harness-MU: A Safe, Governed, and Effective Harness for Multi-User LLM Agents
|
Jun 16, 2026 |
|
[Daily Paper] From AGI to ASI
|
Jun 15, 2026 |
|
[Daily Paper] Revelio: Cost-Efficient Agentic Memory Safety Vulnerability Detection For Repository-Scale Code
|
Jun 14, 2026 |
|
[Daily Paper] Exposing the Illusion of Erasure in Knowledge Editing for Large Language Models
|
Jun 13, 2026 |
|
[Blog] When a Jailbreak Claim Becomes an Export Control: The Disclosure-Norms Gap Behind the Fable 5 / Mythos 5 Suspension
|
Jun 13, 2026 |
|
[Daily Paper] NRT-Bench: Benchmarking Multi-Turn Red-Teaming of LLM Operator Agents in Safety-Critical Environments
|
Jun 12, 2026 |
|
[Daily Paper] Trajectory-Level Redirection Attacks on Vision-Language-Action Models
|
Jun 11, 2026 |
|
[Daily Paper] Analyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic Systems
|
Jun 10, 2026 |
|
[Daily Paper] Local LLM Agents as Vulnerable Runtimes: A Source-Code Audit of the Agent Runtime Layer
|
Jun 09, 2026 |
|
[Report] Report #385 — Where Censorship Lives: A Three-Layer Model of Content Suppression in Chinese-Lab LLMs
|
Jun 08, 2026 |
|
[Daily Paper] ProbeAct: Probe-Guided Training-Free Failure Recovery in Vision-Language-Action Models
|
Jun 08, 2026 |
|
[Daily Paper] Toward Open Weight Models Without Risks: Separating Public and Private Capabilities in Large Language Models
|
Jun 07, 2026 |
|
[Daily Paper] OTTER: A Red-Teaming System for Toxicity-Evading Jailbreak Prompt Optimization
|
Jun 06, 2026 |
|
[Daily Paper] Scalable Hierarchical Attention Transformers for Multi-Turn Jailbreak Detection in Long Conversations
|
Jun 05, 2026 |
|
[Daily Paper] The Geometry of Refusal: Linear Instability in Safety-Aligned LLMs
|
Jun 04, 2026 |
|
[Daily Paper] Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies
|
Jun 03, 2026 |
|
[Daily Paper] Attacking the Trusted Imagination: Oracle-Level Integrity Attacks on Imagine-then-Act World Models
|
Jun 02, 2026 |
|
[Daily Paper] Foundation Protocol: Building the Safety Infrastructure for a Human–AI Society
|
May 31, 2026 |
|
[Daily Paper] Auditing Agent Harness Safety: Why Final Outputs Are Not Enough
|
May 30, 2026 |
|
[Daily Paper] Lipschitz Optimization for Formal Verification of Homographies
|
May 29, 2026 |
|
[Daily Paper] Jailbreak-R1: RL-Trained Automated Red-Teaming with Diversity-Effectiveness Balance
|
May 29, 2026 |
|
[Video] [Blog] Glasswing's Missing Manual
|
May 29, 2026 |
|
[Blog] Glasswing's Missing Manual
|
May 29, 2026 |
|
[Report] Report #372 — Lyria 3 Pro Safety Architecture: Probe Findings V1–V53 (ANTWORT/STURM Series)
|
May 28, 2026 |
|
[Daily Paper] CoP: Agentic Red-Teaming for LLMs via Composition of Principles
|
May 28, 2026 |
|
[Daily Paper] IS-Bench: Evaluating the Interactive Safety of VLM-Driven Embodied Agents in Household Tasks
|
May 27, 2026 |
|
[Daily Paper] AIRTBench: Measuring Autonomous AI Red Teaming Capabilities in Language Models
|
May 26, 2026 |
|
[Blog] How ModelAtlas Scores 704 AI Models for Trust
|
May 26, 2026 |
|
[Video] [Blog] Quoting Both: The Encyclical and Olah on AI Interiority
|
May 26, 2026 |
|
[Blog] Quoting Both: The Encyclical and Olah on AI Interiority
|
May 26, 2026 |
|
[Daily Paper] Cultural Adaptation in Large Language Models for Political Discourse
|
May 25, 2026 |
|
[Daily Paper] Align to Misalign: Automatic LLM Jailbreak with Meta-Optimized LLM Judges
|
May 24, 2026 |
|
[Video] [Blog] Project Glasswing's Buried Number
|
May 24, 2026 |
|
[Blog] Project Glasswing's Buried Number
|
May 24, 2026 |
|
[Daily Paper] BitBypass: A New Direction in Jailbreaking Aligned LLMs with Bitstream Camouflage
|
May 23, 2026 |
|
[Daily Paper] Jailbreak-R1: Exploring the Jailbreak Capabilities of LLMs via Reinforcement Learning
|
May 22, 2026 |
|
[Daily Paper] CoP: Agentic Red-teaming for Large Language Models using Composition of Principles
|
May 21, 2026 |
|
[Daily Paper] 10 Open Challenges Steering the Future of Vision-Language-Action Models
|
May 20, 2026 |
|
[Blog] Moral Formation Isn't Enough: What Happens When AI Values Break Under Pressure
|
May 20, 2026 |
|
[Daily Paper] Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics
|
May 19, 2026 |
|
[Daily Paper] Goal-oriented Backdoor Attack against Vision-Language-Action Models via Physical Objects
|
May 18, 2026 |
|
[Daily Paper] Attention-Guided Patch-Wise Sparse Adversarial Attacks on Vision-Language-Action Models
|
May 17, 2026 |
|
[Daily Paper] FreezeVLA: Action-Freezing Attacks against Vision-Language-Action Models
|
May 16, 2026 |
|
[Blog] ModelAtlas Methodology: What an FLIP-Graded ASR Signal Can and Cannot Tell You
|
May 16, 2026 |
|
[Daily Paper] The Price of Agreement: Measuring LLM Sycophancy in Agentic Financial Applications
|
May 15, 2026 |
|
[Blog] The Biggest Threat to Robot Safety Isn't Hackers — It's Everyone Else
|
May 15, 2026 |
|
[Video] [Blog] Compute Is Not Governance: Anthropic's 2028 Scenarios and the Missing Institutions of Democratic AI
|
May 15, 2026 |
|
[Blog] Compute Is Not Governance: Anthropic's 2028 Scenarios and the Missing Institutions of Democratic AI
|
May 15, 2026 |
|
[Daily Paper] AsyncShield: A Plug-and-Play Edge Adapter for Asynchronous Cloud-based VLA Navigation
|
May 14, 2026 |
|
[Daily Paper] Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms
|
May 13, 2026 |
|
[Daily Paper] Lifelong Safety Alignment for Language Models
|
May 13, 2026 |
|
[Video] [Blog] Robot Dogs Are a Security Nightmare — And We Can Prove It
|
May 13, 2026 |
|
[Blog] Robot Dogs Are a Security Nightmare — And We Can Prove It
|
May 13, 2026 |
|
[Daily Paper] Task-specific Subnetwork Discovery in Reinforcement Learning for Autonomous Underwater Navigation
|
May 12, 2026 |
|
[Daily Paper] A Deployable Embodied Vision-Language Navigation System with Hierarchical Cognition and Context-Aware Exploration
|
May 11, 2026 |
|
[Daily Paper] Reinforcing 3D Understanding in Point-VLMs via Geometric Reward Credit Assignment
|
May 10, 2026 |
|
[Daily Paper] The Alignment Tax: An Open Question for Embodied AI Economics
|
May 09, 2026 |
|
[Daily Paper] SoK: Robustness in Large Language Models against Jailbreak Attacks
|
May 09, 2026 |
|
[Daily Paper] PokeVLA: Empowering Pocket-Sized Vision-Language-Action Model with Comprehensive World Knowledge Guidance
|
May 09, 2026 |
|
[Daily Paper] Graceful Degradation Policies for Embodied Agents under Uncertainty-Bounded Action
|
May 08, 2026 |
|
[Daily Paper] Integrating Anomaly Detection into Agentic AI for Proactive Risk Management in Human Activity
|
May 08, 2026 |
|
[Daily Paper] MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety
|
May 07, 2026 |
|
[Daily Paper] From Signal Degradation to Computation Collapse: Uncovering the Two Failure Modes of LLM Quantization
|
May 07, 2026 |
|
[Daily Paper] Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses
|
May 06, 2026 |
|
[Daily Paper] Can Continual Pre-training Bridge the Performance Gap between General-purpose and Specialized Language Models in the Medical Domain?
|
May 06, 2026 |
|
[Daily Paper] ROBOGATE: Adaptive Failure Discovery for Safe Robot Policy Deployment via Two-Stage Boundary-Focused Sampling
|
May 05, 2026 |
|
[Daily Paper] Evaluating the Robustness of Large Language Model Safety Guardrails Against Adversarial Attacks
|
May 05, 2026 |
|
[Daily Paper] Pause or Fabricate? Training Language Models for Grounded Reasoning
|
May 05, 2026 |
|
[Report] EXP-680 — Eval-Awareness × Deliberative Prompting Interaction (Structural Null Finding)
|
May 04, 2026 |
|
[Daily Paper] Vision-Language-Action Models: Concepts, Progress, Applications and Challenges
|
May 04, 2026 |
|
[Daily Paper] RECAP: A Resource-Efficient Method for Adversarial Prompting in Large Language Models
|
May 04, 2026 |
|
[Daily Paper] RoboWM-Bench: A Benchmark for Evaluating World Models in Robotic Manipulation
|
May 04, 2026 |
|
[Daily Paper] When World Models Dream Wrong: Physical-Conditioned Adversarial Attacks against World Models
|
May 03, 2026 |
|
[Daily Paper] A Comparative Evaluation of AI Agent Security Guardrails
|
May 03, 2026 |
|
[Daily Paper] SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models
|
May 03, 2026 |
|
[Video] [Daily Paper] VeriGuard: Enhancing LLM Agent Safety via Verified Code Generation
|
May 02, 2026 |
|
[Daily Paper] VeriGuard: Enhancing LLM Agent Safety via Verified Code Generation
|
May 02, 2026 |
|
[Video] [Daily Paper] Implicit Jailbreak Attacks via Cross-Modal Information Concealment on Vision-Language Models
|
May 02, 2026 |
|
[Daily Paper] Cross-Modal Prompt Injection: Physical-World Text Attacks on Embodied Agents
|
May 02, 2026 |
|
[Daily Paper] XEmbodied: A Foundation Model with Enhanced Geometric and Physical Cues for Large-Scale Embodied Environments
|
May 02, 2026 |
|
[Daily Paper] Fringe Projection Based Vision Pipeline for Autonomous Hard Drive Disassembly
|
May 01, 2026 |
|
[Daily Paper] RedAgent: Red Teaming Large Language Models with Context-aware Autonomous Language Agent
|
Apr 30, 2026 |
|
[Daily Paper] Recoverability as an Evaluation Axis: When Embodied Agents Can Undo Mistakes
|
Apr 30, 2026 |
|
[Daily Paper] Low-Resource Languages Jailbreak GPT-4
|
Apr 30, 2026 |
|
[Daily Paper] Greedy Kalman-Swarm: Improving State Estimation in Robot Swarms in Harsh Environments
|
Apr 30, 2026 |
|
[Daily Paper] Towards Physically Realizable Adversarial Attacks in Embodied Vision Navigation
|
Apr 29, 2026 |
|
[Daily Paper] LlamaFirewall: An Open Source Guardrail System for Building Secure AI Agents
|
Apr 29, 2026 |
|
[Daily Paper] Rule-VLN: Bridging Perception and Compliance via Semantic Reasoning and Geometric Rectification
|
Apr 29, 2026 |
|
[Video] [Daily Paper] Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms
|
Apr 28, 2026 |
|
[Daily Paper] Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms
|
Apr 28, 2026 |
|
[Daily Paper] ARMOR: Aligning Secure and Safe Large Language Models via Meticulous Reasoning
|
Apr 28, 2026 |
|
[Daily Paper] StableIDM: Stabilizing Inverse Dynamics Model against Manipulator Truncation via Spatio-Temporal Refinement
|
Apr 28, 2026 |
|
[Daily Paper] Using Large Language Models for Embodied Planning Introduces Systematic Safety Risks
|
Apr 27, 2026 |
|
[Daily Paper] Refusal Falls off a Cliff: How Safety Alignment Fails in Reasoning Models
|
Apr 27, 2026 |
|
[Daily Paper] Robust Multispectral Semantic Segmentation under Missing or Full Modalities via Structured Latent Projection
|
Apr 27, 2026 |
|
[Daily Paper] Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks
|
Apr 26, 2026 |
|
[Daily Paper] An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challenges
|
Apr 26, 2026 |
|
[Daily Paper] CART: Context-Aware Terrain Adaptation using Temporal Sequence Selection for Legged Robots
|
Apr 26, 2026 |
|
[Report] Heuristic vs FLIP Grader Divergence: Three-Cohort Triangulation (2026-04-25)
|
Apr 25, 2026 |
|
[Report] Wave 7 HANSE Dataset — leela_evolved_v0.2
|
Apr 25, 2026 |
|
[Daily Paper] FailSafe: Reasoning and Recovery from Failures in Vision-Language-Action Models
|
Apr 25, 2026 |
|
[Daily Paper] C-ΔΘ: Circuit-Restricted Weight Arithmetic for Selective Refusal
|
Apr 25, 2026 |
|
[Blog] Your AI Safety Numbers May Be Wrong By 80 Points
|
Apr 25, 2026 |
|
[Report] Threat Horizon Addendum (2026-04-24) — Grading-Rigor as a Threat-Horizon Variable
|
Apr 24, 2026 |
|
[Report] Crescendo Frontier S24 — FLIP Re-Graded Addendum (deepseek-r1:8b)
|
Apr 24, 2026 |
|
[Report] Governance Lag Index: Formal Methodology and Worked Example (Q2 2026)
|
Apr 24, 2026 |
|
[Report] Heuristic vs FLIP Grader Calibration: An 82pp Over-Report on Gemma 4 Temporal Laundering
|
Apr 24, 2026 |
|
[Report] Temporal Laundering Frontier Cohort Analysis
|
Apr 24, 2026 |
|
[Report] Threat Horizon — Q2/Q3 2026 (Post-GPT-5.5 Window)
|
Apr 24, 2026 |
|
[Report] Q2 2026 Research Agenda
|
Apr 24, 2026 |
|
[Daily Paper] Symbolic Guardrails for Domain-Specific Agents: Stronger Safety and Security Guarantees Without Sacrificing Utility
|
Apr 24, 2026 |
|
[Daily Paper] Reasoned Safety Alignment: Ensuring Jailbreak Defense via Answer-Then-Check
|
Apr 24, 2026 |
|
[Daily Paper] LIBERO-X: Robustness Litmus for Vision-Language-Action Models
|
Apr 24, 2026 |
|
[Daily Paper] Attention-Guided Patch-Wise Sparse Adversarial Attacks on Vision-Language-Action Models
|
Apr 24, 2026 |
|
[Daily Paper] Weak-to-Strong Jailbreaking on Large Language Models
|
Apr 23, 2026 |
|
[Daily Paper] There Will Be a Scientific Theory of Deep Learning
|
Apr 23, 2026 |
|
[Daily Paper] SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models
|
Apr 23, 2026 |
|
[Daily Paper] Updating Robot Safety Representations Online from Natural Language Feedback
|
Apr 22, 2026 |
|
[Daily Paper] Beyond I'm Sorry, I Can't: Dissecting Large Language Model Refusal
|
Apr 22, 2026 |
|
[Daily Paper] UMI-3D: Extending Universal Manipulation Interface from Vision-Limited to 3D Spatial Perception
|
Apr 21, 2026 |
|
[Daily Paper] SpaceMind: A Modular and Self-Evolving Embodied Vision-Language Agent Framework for Autonomous On-orbit Servicing
|
Apr 21, 2026 |
|
[Daily Paper] HomeSafe-Bench: Evaluating Vision-Language Models on Unsafe Action Detection for Embodied Agents in Household Scenarios
|
Apr 21, 2026 |
|
[Daily Paper] DR$^{3}$-Eval: Towards Realistic and Reproducible Deep Research Evaluation
|
Apr 21, 2026 |
|
[Daily Paper] Be Your Own Red Teamer: Safety Alignment via Self-Play and Reflective Experience Replay
|
Apr 21, 2026 |
|
[Daily Paper] DualTHOR: A Dual-Arm Humanoid Simulation Platform for Contingency-Aware Planning
|
Apr 20, 2026 |
|
[Daily Paper] Align to Misalign: Automatic LLM Jailbreak with Meta-Optimized LLM Judges
|
Apr 20, 2026 |
|
[Daily Paper] EmbodiedGovBench: A Benchmark for Governance, Recovery, and Upgrade Safety in Embodied Agent Systems
|
Apr 20, 2026 |
|
[Daily Paper] Few Tokens Matter: Entropy Guided Attacks on Vision-Language Models
|
Apr 19, 2026 |
|
[Daily Paper] A Benchmark for Evaluating Outcome-Driven Constraint Violations in Autonomous AI Agents
|
Apr 19, 2026 |
|
[Daily Paper] 10 Open Challenges Steering the Future of Vision-Language-Action Models
|
Apr 17, 2026 |
|
[Daily Paper] RACF: A Resilient Autonomous Car Framework with Object Distance Correction
|
Apr 17, 2026 |
|
[Daily Paper] LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet
|
Apr 17, 2026 |
|
[Daily Paper] Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey
|
Apr 16, 2026 |
|
[Daily Paper] Do LLMs Have Political Correctness? Analyzing Ethical Biases and Jailbreak Vulnerabilities in AI Systems
|
Apr 16, 2026 |
|
[Daily Paper] Enhancing Model Defense Against Jailbreaks with Proactive Safety Reasoning
|
Apr 15, 2026 |
|
[Daily Paper] AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation
|
Apr 15, 2026 |
|
[Daily Paper] A Physical Agentic Loop for Language-Guided Grasping with Execution-State Monitoring
|
Apr 15, 2026 |
|
[Daily Paper] When Alignment Fails: Multimodal Adversarial Attacks on Vision-Language-Action Models
|
Apr 14, 2026 |
|
[Daily Paper] Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations
|
Apr 14, 2026 |
|
[Daily Paper] Aligning Agents via Planning: A Benchmark for Trajectory-Level Reward Modeling
|
Apr 14, 2026 |
|
[Report] SmolVLA Action-Layer Adversarial Pilot — Null Result at 450M Scale
|
Apr 13, 2026 |
|
[Daily Paper] TraceSafe: A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectories
|
Apr 13, 2026 |
|
[Daily Paper] Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations
|
Apr 13, 2026 |
|
[Daily Paper] BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization
|
Apr 13, 2026 |
|
[Daily Paper] When Alignment Fails: Multimodal Adversarial Attacks on Vision-Language-Action Models
|
Apr 12, 2026 |
|
[Video] [Daily Paper] Hazard Management in Robot-Assisted Mammography Support
|
Apr 12, 2026 |
|
[Daily Paper] Hazard Management in Robot-Assisted Mammography Support
|
Apr 12, 2026 |
|
[Daily Paper] The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training
|
Apr 12, 2026 |
|
[Video] [Report] Meta-Jailbreak in NotebookLM, a Slide-Deck Content Filter, and a Methodology Lesson
|
Apr 11, 2026 |
|
[Daily Paper] Replicating TEMPEST at Scale: Multi-Turn Adversarial Attacks Against Trillion-Parameter Frontier Models
|
Apr 11, 2026 |
|
[Daily Paper] Benchmarking Adversarial Robustness to Bias Elicitation in Large Language Models: Scalable Automated Assessment with LLM-as-a-Judge
|
Apr 11, 2026 |
|
[Video] [Daily Paper] ROSClaw: A Hierarchical Semantic-Physical Framework for Heterogeneous Multi-Agent Collaboration
|
Apr 11, 2026 |
|
[Daily Paper] ROSClaw: A Hierarchical Semantic-Physical Framework for Heterogeneous Multi-Agent Collaboration
|
Apr 11, 2026 |
|
[Blog] A Meta-Jailbreak, a Slide-Deck Content Filter, and a CLI That Lied to Us
|
Apr 11, 2026 |
|
[Report] Crescendo Frontier S24 — Multi-Turn Escalation Across Six Frontier Models
|
Apr 10, 2026 |
|
[Daily Paper] GuardReasoner: Towards Reasoning-based LLM Safeguards
|
Apr 10, 2026 |
|
[Daily Paper] Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial Patches
|
Apr 10, 2026 |
|
[Video] [Daily Paper] Uncovering Linguistic Fragility in Vision-Language-Action Models via Diversity-Aware Red Teaming
|
Apr 10, 2026 |
|
[Daily Paper] Uncovering Linguistic Fragility in Vision-Language-Action Models via Diversity-Aware Red Teaming
|
Apr 10, 2026 |
|
[Daily Paper] AttackVLA: Benchmarking Adversarial and Backdoor Attacks on Vision-Language-Action Models
|
Apr 09, 2026 |
|
[Daily Paper] Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw
|
Apr 08, 2026 |
|
[Daily Paper] LIBERO-Para: A Diagnostic Benchmark and Metrics for Paraphrase Robustness in VLA Models
|
Apr 08, 2026 |
|
[Report] Format-Lock Mid-Range Experiment — Perfect Compliance in 3-8B Models
|
Apr 07, 2026 |
|
[Report] Gemma 4 (31B) Safety Profile — Cross-Attack Synthesis
|
Apr 07, 2026 |
|
[Report] Authority Gradient Benchmark — Claimed Authority as Safety Override Vector Across 3 Models
|
Apr 07, 2026 |
|
[Report] Crescendo Multi-Turn Escalation — 3-Model Replication on Embodied AI Scenarios
|
Apr 07, 2026 |
|
[Daily Paper] X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents
|
Apr 07, 2026 |
|
[Daily Paper] AttackVLA: Benchmarking Adversarial and Backdoor Attacks on Vision-Language-Action Models
|
Apr 07, 2026 |
|
[Daily Paper] AgentWatcher: A Rule-based Prompt Injection Monitor
|
Apr 07, 2026 |
|
[Report] DeepInception on Embodied AI Scenarios — Nested Dream Attacks Against 4 Models
|
Apr 06, 2026 |
|
[Report] Gemma 4 (31B) and Mistral Small 4 (119B MoE) — New Model Safety Evaluation
|
Apr 06, 2026 |
|
[Daily Paper] Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics
|
Apr 06, 2026 |
|
[Daily Paper] Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming
|
Apr 06, 2026 |
|
[Daily Paper] ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers
|
Apr 06, 2026 |
|
[Report] Pliny Full Corpus Validation — 149 Scenarios x 4 Models, FLIP-Graded
|
Apr 05, 2026 |
|
[Daily Paper] ANNIE: Be Careful of Your Robots — Adversarial Safety Attacks on Embodied AI
|
Apr 05, 2026 |
|
[Daily Paper] Structured Visual Narratives Undermine Safety Alignment in Multimodal Large Language Models
|
Apr 04, 2026 |
|
[Daily Paper] GameplayQA: A Benchmarking Framework for Decision-Dense POV-Synced Multi-Video Understanding of 3D Virtual Agents
|
Apr 03, 2026 |
|
[Daily Paper] BadRobot: Jailbreaking Embodied LLM Agents in the Physical World
|
Apr 02, 2026 |
|
[Blog] Everything Hidden: ST3GG and the Steganographic Attack Surface for AI Systems
|
Apr 02, 2026 |
|
[Report] L3/L8 Evolved Attack Variants — S20 Adversarial Refinement
|
Apr 01, 2026 |
|
[Daily Paper] Automated Red-Teaming Framework for Large Language Model Security Assessment
|
Apr 01, 2026 |
|
[Daily Paper] Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses
|
Mar 30, 2026 |
|
[Blog] Eight Layers of Visual Jailbreaks: Why ASCII Art Is Patched But Framing Attacks Aren't
|
Mar 30, 2026 |
|
[Blog] Eight Layers of Visual Jailbreaks: Why ASCII Art Is Patched But the Transcription Loophole Isn't
|
Mar 30, 2026 |
|
[Daily Paper] AutoRedTeamer: Autonomous Red Teaming with Lifelong Attack Integration
|
Mar 29, 2026 |
|
[Report] Defense Benchmark Data Consolidation for CCS Paper
|
Mar 28, 2026 |
|
[Report] Independence Scorecard March 2026 Update -- Anthropic Court Victory, OpenAI Mission Shift
|
Mar 28, 2026 |
|
[Report] Paired Format-Lock + L1B3RT4S Orthogonality Test
|
Mar 28, 2026 |
|
[Daily Paper] TopoPilot: Reliable Conversational Workflow Automation for Topological Data Analysis and Visualization
|
Mar 28, 2026 |
|
[Blog] The 67% Wall: Why Every AI Model Falls to the Same Jailbreak Rate
|
Mar 28, 2026 |
|
[Blog] Same Defense, Opposite Result: Why AI Safety Depends on Which Model You're Protecting
|
Mar 28, 2026 |
|
[Blog] When Your Defense Is on the Wrong Floor: Why System-Prompt Safety Fails Against Persona Hijacking
|
Mar 28, 2026 |
|
[Report] L1B3RT4S VLA Adaptation and DETECTED_PROCEEDS Scaling Analysis
|
Mar 27, 2026 |
|
[Report] Cross-Attack Family Synthesis
|
Mar 27, 2026 |
|
[Report] - L1B3RT45 Corpus: 10-Model Cross-Scale Synthesis
|
Mar 27, 2026 |
|
[Report] - L1B3RT45 Full Corpus Cross-Model Analysis
|
Mar 27, 2026 |
|
[Report] Sampling Parameter Manipulation as a Novel Attack Surface -- Pilot Results
|
Mar 27, 2026 |
|
[Report] L1B3RT4S Cross-Scale Effectiveness Analysis
|
Mar 27, 2026 |
|
[Video] [Daily Paper] G0DM0D3: A Modular Framework for Evaluating LLM Robustness Through Adaptive Sampling and Input Perturbation
|
Mar 27, 2026 |
|
[Daily Paper] G0DM0D3: A Modular Framework for Evaluating LLM Robustness Through Adaptive Sampling and Input Perturbation
|
Mar 27, 2026 |
|
[Report] Actionable Defense Recommendations from Sprint 15
|
Mar 25, 2026 |
|
[Report] VLA Adversarial Landscape — 33 Families, 673+ Traces
|
Mar 25, 2026 |
|
[Report] Sprint 15 Comprehensive Benchmark Analysis
|
Mar 25, 2026 |
|
[Report] VLA Data Curation Summary -- Sprint 15 R1+R2
|
Mar 25, 2026 |
|
[Report] Defense Landscape Analysis — What Works and What Doesn't
|
Mar 25, 2026 |
|
[Report] Emotional Manipulation Attack Family -- Deep Dive
|
Mar 25, 2026 |
|
[Report] Format-Lock Mid-Range Experiment
|
Mar 25, 2026 |
|
[Report] AIES Paper Scoping and CCA Disclosure Framework — Ethics Analysis
|
Mar 25, 2026 |
|
[Report] DETECTED_PROCEEDS Reasoning Anatomy
|
Mar 25, 2026 |
|
[Report] DETECTED_PROCEEDS Provider Signature Mechanics
|
Mar 25, 2026 |
|
[Report] Free-Tier Safety Equity — Differential Jailbreak Vulnerability by API Pricing Tier
|
Mar 25, 2026 |
|
[Report] Corpus Pattern Mining II — Six Novel Empirical Findings
|
Mar 25, 2026 |
|
[Report] Evolution Run 1 Mutation Analysis and Next-Generation Strategy Design
|
Mar 25, 2026 |
|
[Report] Cross-Jurisdictional Regulatory Gap Analysis — VLA Attack Families vs. Regulatory Coverage
|
Mar 25, 2026 |
|
[Report] Format-Lock Defense Research — Five Countermeasure Architectures
|
Mar 25, 2026 |
|
[Report] Ethics of Universal Attacks — Disclosure Obligations for Architectural Vulnerabilities
|
Mar 25, 2026 |
|
[Report] Defense Co-Evolution Results
|
Mar 25, 2026 |
|
[Report] Corpus Expansion -- Ollama Cloud Trace Import
|
Mar 25, 2026 |
|
[Report] Format-Lock Midrange Experiment — The 4-14B Data Gap Filled
|
Mar 25, 2026 |
|
[Report] Frontier Model Safety Scorecards
|
Mar 25, 2026 |
|
[Report] Kimi K2.5 Frontier Analysis — 1.1TB MoE at the Safety Scaling Boundary
|
Mar 25, 2026 |
|
[Report] Ambiguous Calibration Results -- 6-Grader Inter-Rater Agreement
|
Mar 25, 2026 |
|
[Report] CCA + GE Expansion -- New Models and Defense Mutations
|
Mar 25, 2026 |
|
[Report] Haiku Re-Grading of Sprint 13 Corpus
|
Mar 25, 2026 |
|
[Report] Cross-Model x Attack-Family ASR Heatmap
|
Mar 25, 2026 |
|
[Report] Wave 7 Validation Results
|
Mar 25, 2026 |
|
[Report] Grader Confusion Matrix and Inter-Grader Agreement Analysis
|
Mar 25, 2026 |
|
[Report] Compliance Cascade Attack -- Frontier Scaling and Co-Evolution Design
|
Mar 25, 2026 |
|
[Report] Haiku Re-Grading Campaign -- Ollama Cloud Traces
|
Mar 25, 2026 |
|
[Report] Epistemic Crisis Grader Calibration Evaluation
|
Mar 25, 2026 |
|
[Report] Statistical Power Analysis for Key Comparisons
|
Mar 25, 2026 |
|
[Report] FLIP Grader Calibration Analysis
|
Mar 25, 2026 |
|
[Report] Corpus-Level Statistical Meta-Analysis
|
Mar 25, 2026 |
|
[Daily Paper] Zero of 36: No AI Attack Family Is Fully Regulated Anywhere in the World
|
Mar 25, 2026 |
|
[Daily Paper] When Defenses Backfire: Five Ways AI Safety Measures Create the Harms They Prevent
|
Mar 25, 2026 |
|
[Daily Paper] Threat Horizon Q2 2026: Agents Go Rogue, Robots Go Offline, Regulators Go Slow
|
Mar 25, 2026 |
|
[Daily Paper] Safety as a Paid Feature: How Free-Tier AI Models Are Less Safe Than Their Paid Counterparts
|
Mar 25, 2026 |
|
[Daily Paper] GoBA: Goal-oriented Backdoor Attack against VLA via Physical Objects
|
Mar 25, 2026 |
|
[Blog] When Defenses Backfire: Five Ways AI Safety Measures Create the Harms They Prevent
|
Mar 25, 2026 |
|
[Blog] Threat Horizon Q2 2026: Agents Go Rogue, Robots Go Offline, Regulators Go Slow
|
Mar 25, 2026 |
|
[Blog] Threat Horizon Digest: March 2026
|
Mar 25, 2026 |
|
[Blog] Temporal Drift: The Boiling Frog Attack on AI Safety
|
Mar 25, 2026 |
|
[Blog] The State of AI Safety: Q1 2026
|
Mar 25, 2026 |
|
[Blog] Safety Awareness Does Not Equal Safety: The 88.9% Problem
|
Mar 25, 2026 |
|
[Blog] Introducing Structured Safety Assessments for Embodied AI
|
Mar 25, 2026 |
|
[Blog] Our Research Papers
|
Mar 25, 2026 |
|
[Blog] Three Providers, Three Architectures, Three Orders of Magnitude: Reasoning-Level DETECTED_PROCEEDS Is Not an Edge Case
|
Mar 25, 2026 |
|
[Blog] Frontier Model Safety: Why 1.1 Trillion Parameters Does Not Mean Safe
|
Mar 25, 2026 |
|
[Blog] F1-STD-001: A Voluntary Standard for AI Safety Evaluation
|
Mar 25, 2026 |
|
[Blog] The Ethics of Emotional AI Manipulation: When Empathy Becomes an Attack Vector
|
Mar 25, 2026 |
|
[Blog] CARTO: The First AI Red Team Certification
|
Mar 25, 2026 |
|
[Blog] CARTO Beta: First 10 Testers Wanted
|
Mar 25, 2026 |
|
[Blog] Adversarial Robustness Assessment Services
|
Mar 25, 2026 |
|
[Report] Defense Evolver Phase 0 — Automated System Prompt Evolution
|
Mar 24, 2026 |
|
[Report] Corpus Pattern Mining — Five Novel Empirical Findings
|
Mar 24, 2026 |
|
[Report] Controlled Scale-Sweep Experiment Protocol
|
Mar 24, 2026 |
|
[Report] COALESCE Grader Validation and New Model Testing
|
Mar 24, 2026 |
|
[Report] Operation Frontier Sweep — Elite Attack Campaign Against Ollama Cloud Frontier Models
|
Mar 24, 2026 |
|
[Report] Frontier Probe — Ollama Cloud Large-Scale Model Testing
|
Mar 24, 2026 |
|
[Report] Garak Adapter Integration Test Results
|
Mar 24, 2026 |
|
[Report] FLIP vs StrongREJECT Methodology Comparison
|
Mar 24, 2026 |
|
[Report] Attack Technique Effectiveness Ranking (LLM-Graded, Sprint 13)
|
Mar 24, 2026 |
|
[Report] EU AI Act Compliance Update — Reasoning Trace Governance and DETECTED_PROCEEDS
|
Mar 24, 2026 |
|
[Report] Qwen3 Benchmark Overfitting Analysis
|
Mar 24, 2026 |
|
[Report] Inter-Provider Vulnerability Correlation Matrix
|
Mar 24, 2026 |
|
[Report] The PARTIAL Verdict Epidemic -- Anatomy of Safety's Grey Zone
|
Mar 24, 2026 |
|
[Report] Iatrogenic Risks of Rapid Safety Improvement — When 0% ASR Is a Symptom, Not a Cure
|
Mar 24, 2026 |
|
[Report] Arcee AI Trinity Safety Assessment and EU Compliance
|
Mar 24, 2026 |
|
[Report] The Qwen3 "Safety Leap" — Artifact Analysis
|
Mar 24, 2026 |
|
[Report] AdvBench Baseline Analysis — Free-Tier Model Vulnerability to Direct Harmful Requests
|
Mar 24, 2026 |
|
[Report] LFM Thinking 1.2B — DETECTED_PROCEEDS Cross-Model Validation
|
Mar 24, 2026 |
|
[Report] The Failure-First Research Programme: A Meta-Analysis of Ten Papers
|
Mar 24, 2026 |
|
[Report] Competitive Intelligence — AI Safety Red Teaming Market
|
Mar 24, 2026 |
|
[Report] Training Data for Safety Classification
|
Mar 24, 2026 |
|
[Report] Temporal Vulnerability Analysis: Attack Era Evolution (2022-2025)
|
Mar 24, 2026 |
|
[Report] Public Dataset Coverage Analysis
|
Mar 24, 2026 |
|
[Daily Paper] Six New Attack Families: Expanding the Embodied AI Threat Taxonomy
|
Mar 24, 2026 |
|
[Daily Paper] The Insurance Industry's Next Silent Crisis
|
Mar 24, 2026 |
|
[Daily Paper] Safety Re-Emerges at Scale -- But Not the Way You Think
|
Mar 24, 2026 |
|
[Daily Paper] Did Qwen3 Fix AI Safety?
|
Mar 24, 2026 |
|
[Daily Paper] Safety Isn't One-Dimensional: The Geometry That Explains Why AI Guardrails Keep Failing
|
Mar 24, 2026 |
|
[Daily Paper] Iatrogenic Safety: When AI Defenses Cause the Harms They Are Designed to Prevent
|
Mar 24, 2026 |
|
[Daily Paper] The Governance Lag Index at 133 Entries: What Q1 2026 Tells Us About Regulating Embodied AI
|
Mar 24, 2026 |
|
[Daily Paper] FreezeVLA: Action-Freezing Attacks against Vision-Language-Action Models
|
Mar 24, 2026 |
|
[Daily Paper] Our First AdvBench Results: 7 Models, 288 Traces, $0
|
Mar 24, 2026 |
|
[Daily Paper] 8 Out of 10 AI Providers Fail EU Compliance — And the Deadline Is 131 Days Away
|
Mar 24, 2026 |
|
[Daily Paper] When AI Systems Know It's Wrong and Do It Anyway
|
Mar 24, 2026 |
|
[Daily Paper] Should We Publish AI Attacks We Discover?
|
Mar 24, 2026 |
|
[Daily Paper] Anatomy of Effective Jailbreaks: What Makes an Attack Actually Work?
|
Mar 24, 2026 |
|
[Blog] What's New in March 2026: Three Waves, 20 Reports, and 6 New Attack Families
|
Mar 24, 2026 |
|
[Blog] Threat Horizon 2027 -- Updated Predictions (v3)
|
Mar 24, 2026 |
|
[Blog] Six New Attack Families: Expanding the Embodied AI Threat Taxonomy
|
Mar 24, 2026 |
|
[Blog] The Insurance Industry's Next Silent Crisis
|
Mar 24, 2026 |
|
[Blog] Safety Re-Emerges at Scale -- But Not the Way You Think
|
Mar 24, 2026 |
|
[Blog] The Governance Lag Index at 133 Entries: What Q1 2026 Tells Us About Regulating Embodied AI
|
Mar 24, 2026 |
|
[Blog] Free AI Safety Score: Test Your Model in 60 Seconds
|
Mar 24, 2026 |
|
[Blog] 7 Framework Integrations: Run Any Tool, Grade with FLIP
|
Mar 24, 2026 |
|
[Blog] 8 Out of 10 AI Providers Fail EU Compliance — And the Deadline Is 131 Days Away
|
Mar 24, 2026 |
|
[Blog] The Cross-Framework Coverage Matrix: What Red-Teaming Tools Miss
|
Mar 24, 2026 |
|
[Blog] Should We Publish AI Attacks We Discover?
|
Mar 24, 2026 |
|
[Blog] Anatomy of Effective Jailbreaks: What Makes an Attack Actually Work?
|
Mar 24, 2026 |
|
[Blog] The Format-Lock Paradox: Why the Best AI Models Have a Blind Spot for Structured Output Attacks
|
Mar 24, 2026 |
|
[Daily Paper] Reasoning-Oriented Programming: Chaining Semantic Gadgets to Jailbreak Large Vision Language Models
|
Mar 23, 2026 |
|
[Blog] We Were Wrong: AI Safety Defenses Do Work (But Only If You Measure Them Right)
|
Mar 23, 2026 |
|
[Blog] Teaching AI to Evolve Its Own Attacks
|
Mar 23, 2026 |
|
[Blog] We're Publishing Our Iatrogenesis Research -- Here's Why
|
Mar 23, 2026 |
|
[Blog] Five Predictions for AI Safety in Q2 2026
|
Mar 23, 2026 |
|
[Blog] First Evidence That AI Safety Defenses Don't Work (And One That Does)
|
Mar 23, 2026 |
|
[Blog] State of Embodied AI Safety: Q1 2026
|
Mar 22, 2026 |
|
[Blog] The Cure Can Be Worse Than the Disease: Iatrogenic Safety in AI
|
Mar 22, 2026 |
|
[Blog] Capability and Safety Are Not on the Same Axis
|
Mar 22, 2026 |
|
[Daily Paper] Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment
|
Mar 21, 2026 |
|
[Daily Paper] DropVLA: An Action-Level Backdoor Attack on Vision-Language-Action Models
|
Mar 20, 2026 |
|
[Daily Paper] Safety is Non-Compositional: A Formal Framework for Capability-Based AI Systems
|
Mar 19, 2026 |
|
[Blog] Why Safety Benchmarks Disagree: Our Results vs Public Leaderboards
|
Mar 19, 2026 |
|
[Blog] Who Guards the Guardians? The Ethics of AI Safety Research
|
Mar 19, 2026 |
|
[Blog] The Unified Theory of Embodied AI Failure
|
Mar 19, 2026 |
|
[Blog] Scoring Robot Incidents: Introducing the EAISI
|
Mar 19, 2026 |
|
[Blog] The Safety Training ROI Problem: Why Provider Matters 57x More Than Size
|
Mar 19, 2026 |
|
[Blog] When Safety Labs Take Government Contracts: The Independence Question
|
Mar 19, 2026 |
|
[Blog] Safety is Non-Compositional: What a Formal Proof Means for Robot Safety
|
Mar 19, 2026 |
|
[Blog] The Polypharmacy Hypothesis: Can Too Much Safety Make AI Less Safe?
|
Mar 19, 2026 |
|
[Blog] From 66 to 92: How We Built an Incident Database in One Day
|
Mar 19, 2026 |
|
[Blog] Context Collapse: When Operational Rules Overwhelm Safety Training
|
Mar 19, 2026 |
|
[Blog] The Alignment Faking Problem: When AI Behaves Differently Under Observation
|
Mar 19, 2026 |
|
[Blog] 30 Ways to Attack a Robot: The Adversarial Field Manual
|
Mar 19, 2026 |
|
[Report] Alignment Backfire Integration — Cross-Language Safety Failure Validates the Safety Improvement Paradox
|
Mar 18, 2026 |
|
[Video] [Daily Paper] Towards Safer Large Reasoning Models by Promoting Safety Decision-Making before Chain-of-Thought Generation
|
Mar 18, 2026 |
|
[Daily Paper] Towards Safer Large Reasoning Models by Promoting Safety Decision-Making before Chain-of-Thought Generation
|
Mar 18, 2026 |
|
[Daily Paper] Colluding LoRA: A Composite Attack on LLM Safety Alignment
|
Mar 18, 2026 |
|
[Blog] Waymo's School Bus Problem
|
Mar 18, 2026 |
|
[Blog] The Unitree Problem: When Your Robot Dog Has a Backdoor
|
Mar 18, 2026 |
|
[Blog] Uber, Cruise, and the Pattern: When Self-Driving Cars Meet Pedestrians
|
Mar 18, 2026 |
|
[Blog] Sidewalk Robots vs. People Who Need Sidewalks
|
Mar 18, 2026 |
|
[Blog] Safety Mechanisms as Attack Surfaces: The Iatrogenesis of AI Safety
|
Mar 18, 2026 |
|
[Blog] Robots in Extreme Environments: Fukushima, the Ocean Floor, and Outer Space
|
Mar 18, 2026 |
|
[Blog] The Robot That Couldn't Tell a Person from a Box of Peppers
|
Mar 18, 2026 |
|
[Blog] Autonomous Haul Trucks and the Pilbara Problem: Mining's Invisible Safety Crisis
|
Mar 18, 2026 |
|
[Blog] When the Exoskeleton Breaks Your Bones: The Hidden Risk of Wearable Robots
|
Mar 18, 2026 |
|
[Blog] Two Fires, $138 Million in Damage: When Warehouse Robots Crash and Burn
|
Mar 18, 2026 |
|
[Blog] The First Autonomous Kill? What We Know About the Kargu-2 Drone Incident
|
Mar 18, 2026 |
|
[Blog] JekyllBot: When Hospital Robots Get Hacked, Patients Get Hurt
|
Mar 18, 2026 |
|
[Blog] A Robot Danced Too Hard in a Restaurant. The Real Story Is About Stop Buttons.
|
Mar 18, 2026 |
|
[Blog] A Robot That Could Fracture a Human Skull: The Figure AI Whistleblower Case
|
Mar 18, 2026 |
|
[Blog] The Defense Impossibility Theorem: Why No Single Safety Layer Can Protect Embodied AI
|
Mar 18, 2026 |
|
[Blog] When Robots Speed Up the Line, Workers Pay the Price: Amazon's Warehouse Injury Crisis
|
Mar 18, 2026 |
|
[Blog] 65 Deaths and Counting: Tesla's Autopilot and FSD Record
|
Mar 18, 2026 |
|
[Blog] 274 Deaths: What the da Vinci Surgical Robot Data Actually Shows
|
Mar 18, 2026 |
|
[Blog] 137 Days to the EU AI Act: What Embodied AI Companies Need to Know
|
Mar 18, 2026 |
|
[Daily Paper] Alignment Backfire: Language-Dependent Reversal of Safety Interventions Across 16 Languages in LLM Multi-Agent Systems
|
Mar 17, 2026 |
|
[Video] [Daily Paper] Why Agents Compromise Safety Under Pressure
|
Mar 16, 2026 |
|
[Daily Paper] Why Agents Compromise Safety Under Pressure
|
Mar 16, 2026 |
|
[Daily Paper] Experimental Evaluation of Security Attacks on Self-Driving Car Platforms
|
Mar 16, 2026 |
|
[Blog] We Rebooted a Robot by Guessing 1234
|
Mar 16, 2026 |
|
[Blog] The Unintentional Adversary: Why the Biggest Threat to Robot Safety Is Not Hackers
|
Mar 16, 2026 |
|
[Blog] The U-Curve of AI Safety: There's a Sweet Spot, and It's Narrow
|
Mar 16, 2026 |
|
[Blog] The State of Embodied AI Safety, March 2026
|
Mar 16, 2026 |
|
[Report] Safety Instruction Dilution (SID) -- Context Length as Attack Surface
|
Mar 15, 2026 |
|
[Report] Technique Non-Additivity -- Combining Attack Techniques Does Not Improve ASR
|
Mar 15, 2026 |
|
[Daily Paper] A Hazard-Informed Data Pipeline for Robotics Physical Safety
|
Mar 15, 2026 |
|
[Blog] Three Vectors, One Window: The Embodied AI Risk Convergence of 2026
|
Mar 15, 2026 |
|
[Blog] The Embodied AI Threat Triangle: Three Laws That Explain Why Robot Safety Is Structurally Broken
|
Mar 15, 2026 |
|
[Blog] Competence-Danger Coupling: The Capability That Makes Robots Useful Is the Same One That Makes Them Vulnerable
|
Mar 15, 2026 |
|
[Daily Paper] Defensible Design for OpenClaw: Securing Autonomous Tool-Invoking Agents
|
Mar 14, 2026 |
|
[Daily Paper] Blindfold: Jailbreaking Embodied LLMs via Action-level Manipulation
|
Mar 13, 2026 |
|
[Report] Prediction Post-Mortem -- Why SBA FLIP ASR Was Over-Predicted and What It Means
|
Mar 12, 2026 |
|
[Report] AI Safety Research Independence Scorecard
|
Mar 12, 2026 |
|
[Report] VLA Attack Family Effectiveness Ranking
|
Mar 12, 2026 |
|
[Daily Paper] Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models
|
Mar 12, 2026 |
|
[Blog] 5.5 Years: The AI Governance Gap in Numbers
|
Mar 12, 2026 |
|
[Blog] The Attack You Can't See: Why AI Safety Evaluators Miss the Most Dangerous Robot Threats
|
Mar 12, 2026 |
|
[Report] Ethics of the Semantically Benign Attack (SBA) Family
|
Mar 11, 2026 |
|
[Report] Deceptive Alignment Reasoning Vulnerability — The 3.5x Inter-Model Gap
|
Mar 11, 2026 |
|
[Report] Abliteration Resistance and Jailbreak Resistance Are Orthogonal Defense Dimensions
|
Mar 11, 2026 |
|
[Report] OBLITERATUS Telemetry Meta-Analysis -- Weight-Space Liberation and the Limits of Safety Removal
|
Mar 11, 2026 |
|
[Report] Crescendo Multi-Turn Attack Regrade Analysis
|
Mar 11, 2026 |
|
[Report] OBLITERATUS Telemetry Analysis (30,238 Records)
|
Mar 11, 2026 |
|
[Report] HALLUCINATION_REFUSAL as the Text-Only Analog of VLA PARTIAL
|
Mar 11, 2026 |
|
[Report] Deliberation Asymmetry -- Empirical Evidence for the System T / System S Framework
|
Mar 11, 2026 |
|
[Report] Inter-Model Verdict Agreement -- The Reproducibility Problem in Adversarial Safety Evaluation
|
Mar 11, 2026 |
|
[Report] Compliance Without Comprehension — A Unified Theory of Structural Vulnerability in AI Systems
|
Mar 11, 2026 |
|
[Report] Format-Lock Capability Floor — Consolidated Evidence
|
Mar 11, 2026 |
|
[Daily Paper] DeepInception: Hypnotize Large Language Model to Be Jailbreaker
|
Mar 11, 2026 |
|
[Blog] Red-Teaming the Next Generation: Why World Model AI Needs a New Threat Taxonomy
|
Mar 11, 2026 |
|
[Blog] When Your Safety Evaluator Is Wrong: The Classifier Quality Problem
|
Mar 11, 2026 |
|
[Blog] Reasoning Models Think Themselves Into Trouble
|
Mar 11, 2026 |
|
[Blog] No Binding Powers: Australia's AI Safety Institute and the Governance Gap
|
Mar 11, 2026 |
|
[Blog] 30 CVEs and Counting: The MCP Security Crisis That Connects to Your Robot
|
Mar 11, 2026 |
|
[Blog] The Compliance Paradox: When AI Says No But Does It Anyway
|
Mar 11, 2026 |
|
[Blog] Alignment Regression: Why Smarter AI Models Make All AI Less Safe
|
Mar 11, 2026 |
|
[Blog] The Actuator Gap: Where Digital Jailbreaks Become Physical Safety Incidents
|
Mar 11, 2026 |
|
[Blog] The Action Layer Has No Guardrails: Why Text-Based AI Safety Fails for Robots
|
Mar 11, 2026 |
|
[Report] AI Safety Lab Independence — Quantitative Framework for Measurable Independence Metrics
|
Mar 10, 2026 |
|
[Report] AI Safety Lab Independence — Deep Analysis
|
Mar 10, 2026 |
|
[Report] The Format-Lock Capability Floor — Why Structural Compliance Attacks Work Across the Full Model Spectrum
|
Mar 10, 2026 |
|
[Report] Corpus Pattern Mining — Novel Findings from 32,465 Jailbreak Prompts
|
Mar 10, 2026 |
|
[Video] [Daily Paper] Visual Adversarial Examples Jailbreak Aligned Large Language Models
|
Mar 10, 2026 |
|
[Daily Paper] Visual Adversarial Examples Jailbreak Aligned Large Language Models
|
Mar 10, 2026 |
|
[Blog] We Ran a Social Experiment on an AI Agent Network. Nobody Noticed.
|
Mar 10, 2026 |
|
[Blog] Decorative Constraints: The Safety Architecture Term We've Been Missing
|
Mar 10, 2026 |
|
[Blog] The Attack Surface Gradient: From Fully Defended to Completely Exposed
|
Mar 10, 2026 |
|
[Daily Paper] Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
|
Mar 09, 2026 |
|
[Daily Paper] Self-Correcting VLA: Online Action Refinement via Sparse World Imagination
|
Mar 08, 2026 |
|
[Daily Paper] CWM: Contrastive World Models for Action Feasibility Learning in Embodied Agent Pipelines
|
Mar 07, 2026 |
|
[Daily Paper] LiLo-VLA: Compositional Long-Horizon Manipulation via Linked Object-Centric Policies
|
Mar 06, 2026 |
|
[Daily Paper] SPOC: Safety-Aware Planning Under Partial Observability And Physical Constraints
|
Mar 05, 2026 |
|
[Daily Paper] Tacmap: Bridging the Tactile Sim-to-Real Gap via Geometry-Consistent Penetration Depth Map
|
Mar 04, 2026 |
|
[Daily Paper] Towards Intelligible Human-Robot Interaction: An Active Inference Approach to Occluded Pedestrian Scenarios
|
Mar 03, 2026 |
|
[Video] [Daily Paper] Compress the Easy, Explore the Hard: Difficulty-Aware Entropy Regularization for Efficient LLM Reasoning
|
Mar 02, 2026 |
|
[Daily Paper] Compress the Easy, Explore the Hard: Difficulty-Aware Entropy Regularization for Efficient LLM Reasoning
|
Mar 02, 2026 |
|
[Blog] Preparing Our Research for ACM CCS 2026
|
Mar 02, 2026 |
|
[Blog] AI Safety Lab Independence Under Government Pressure: A Structural Analysis
|
Mar 02, 2026 |
|
[Report] Reinforcement Learning as a Deception Amplifier: Reward Shaping Risks in Embodied AI Systems
|
Mar 01, 2026 |
|
[Report] Human-in-the-Loop Failure Modes in Embodied AI Oversight
|
Mar 01, 2026 |
|
[Report] Adversarial AI Failure Modes in Australian Workplaces
|
Mar 01, 2026 |
|
[Daily Paper] LessMimic: Long-Horizon Humanoid Interaction with Unified Distance Field Representations
|
Mar 01, 2026 |
|
[Blog] Why AI Safety Rules Always Arrive Too Late
|
Mar 01, 2026 |
|
[Blog] When the Robot Body Changes but the Exploit Doesn't
|
Mar 01, 2026 |
|
[Blog] Introducing the Tool-Chain Adversarial Dataset: 26 Scenarios Across 4 Attack Classes
|
Mar 01, 2026 |
|
[Blog] The AI That Lies About How It Thinks
|
Mar 01, 2026 |
|
[Blog] The 50-Turn Sleeper: How Agents Hide Instructions in Plain Sight
|
Mar 01, 2026 |
|
[Blog] Red Team Assessment Methodology for Embodied AI: Eight Dimensions the Current Market Doesn't Cover
|
Mar 01, 2026 |
|
[Blog] The Promptware Kill Chain: How Agentic Systems Get Compromised
|
Mar 01, 2026 |
|
[Blog] Product Liability and the Embodied AI Manufacturer: Adversarial Testing as Legal Due Diligence
|
Mar 01, 2026 |
|
[Blog] What the NSW Digital Work Systems Act Means for Your AI Deployment
|
Mar 01, 2026 |
|
[Blog] Instruction-Hierarchy Subversion in Long-Horizon Agentic Execution
|
Mar 01, 2026 |
|
[Blog] Inference Trace Manipulation as an Adversarial Attack Surface
|
Mar 01, 2026 |
|
[Blog] Deceptive Alignment Detection Under Evaluation-Aware Conditions
|
Mar 01, 2026 |
|
[Blog] Cross-Embodiment Adversarial Transfer in Vision-Language-Action Models
|
Mar 01, 2026 |
|
[Blog] Can You Catch an AI That Knows It's Being Watched?
|
Mar 01, 2026 |
|
[Blog] Australian AI Safety Frameworks and the Embodied AI Gap
|
Mar 01, 2026 |
|
[Blog] Attack Taxonomy Convergence: Where Six Adversarial AI Frameworks Agree
|
Mar 01, 2026 |
|
[Blog] Actuarial Risk Modelling for Embodied AI: What Insurers Need and What Research Provides
|
Mar 01, 2026 |
|
[Daily Paper] SignVLA: A Gloss-Free Vision-Language-Action Framework for Real-Time Sign Language-Guided Robotic Manipulation
|
Feb 28, 2026 |
|
[Daily Paper] OpenRT: An Open-Source Red Teaming Framework for Multimodal Large Language Models
|
Feb 27, 2026 |
|
[Blog] Why Reasoning Models Are More Vulnerable to Multi-Turn Attacks
|
Feb 27, 2026 |
|
[Blog] What the NSW Digital Work Systems Bill Means for AI Deployers
|
Feb 27, 2026 |
|
[Blog] What LLM Vulnerabilities Mean for Robots
|
Feb 27, 2026 |
|
[Blog] Your AI Safety Classifier Is Probably Wrong: The 2.3x Overcount Problem
|
Feb 27, 2026 |
|
[Daily Paper] SafeDialBench: A Fine-Grained Safety Evaluation Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks
|
Feb 26, 2026 |
|
[Blog] Australia's AI Safety Institute: A Mandated Gap and Where Failure-First Research Fits
|
Feb 26, 2026 |
|
[Daily Paper] ActionReasoning: Robot Action Reasoning in 3D Space with LLM for Robotic Brick Stacking
|
Feb 25, 2026 |
|
[Blog] Building a Daily Research Digest with NotebookLM and Claude Code
|
Feb 25, 2026 |
|
[Daily Paper] HALO: A Unified Vision-Language-Action Model for Embodied Multimodal Chain-of-Thought Reasoning
|
Feb 24, 2026 |
|
[Daily Paper] From Perception to Action: An Interactive Benchmark for Vision Reasoning
|
Feb 23, 2026 |
|
[Daily Paper] EKF-Based Depth Camera and Deep Learning Fusion for UAV-Person Distance Estimation and Following in SAR Operations
|
Feb 22, 2026 |
|
[Daily Paper] Pressure Reveals Character: Behavioural Alignment Evaluation at Depth
|
Feb 21, 2026 |
|
[Daily Paper] Fuz-RL: A Fuzzy-Guided Robust Framework for Safe Reinforcement Learning under Uncertainty
|
Feb 20, 2026 |
|
[Blog] The Faithfulness Gap: When Models Follow Format But Refuse Content
|
Feb 20, 2026 |
|
[Daily Paper] Assessing Risks of Large Language Models in Mental Health Support: A Framework for Automated Clinical AI Red Teaming
|
Feb 19, 2026 |
|
[Daily Paper] Safe and Interpretable Multimodal Path Planning for Multi-Agent Cooperation
|
Feb 18, 2026 |
|
[Daily Paper] A User-driven Design Framework for Robotaxi
|
Feb 17, 2026 |
|
[Daily Paper] Small Reward Models via Backward Inference
|
Feb 16, 2026 |
|
[Daily Paper] Agentic AI and the Cyber Arms Race
|
Feb 15, 2026 |
|
[Daily Paper] Distraction is All You Need for Multimodal Large Language Model Jailbreaking
|
Feb 14, 2026 |
|
[Blog] Can Invented Languages Bypass AI Safety Filters?
|
Feb 14, 2026 |
|
[Daily Paper] Alignment faking in large language models
|
Feb 13, 2026 |
|
[Daily Paper] Scaling Trends for Data Poisoning in LLMs
|
Feb 12, 2026 |
|
[Report] Procedural Language Generation as Attack Surface
|
Feb 11, 2026 |
|
[Daily Paper] Can Large Language Models Automatically Jailbreak GPT-4V?
|
Feb 11, 2026 |
|
[Daily Paper] Jailbreak Attacks and Defenses Against Large Language Models: A Survey
|
Feb 10, 2026 |
|
[Daily Paper] WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models
|
Feb 09, 2026 |
|
[Daily Paper] When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search
|
Feb 08, 2026 |
|
[Blog] Supply Chain Poisoning: Why Small Models Show Near-Total Vulnerability
|
Feb 08, 2026 |
|
[Daily Paper] JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
|
Feb 07, 2026 |
|
[Daily Paper] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
|
Feb 06, 2026 |
|
[Blog] Policy Corpus Synthesis: Five Structural Insights From 12 Deep Research Reports
|
Feb 06, 2026 |
|
[Report] Cross-Model Vulnerability Inheritance in Multi-Agent Systems
|
Feb 05, 2026 |
|
[Daily Paper] Security and Privacy Challenges of Large Language Models: A Survey
|
Feb 05, 2026 |
|
[Report] RETRACTED — Capability Does Not Imply Safety: Empirical Evidence from Jailbreak Archaeology Across Eight Foundation Models
|
Feb 04, 2026 |
|
[Report] CERTIFIED EMBODIED INTELLIGENCE: A COMPREHENSIVE FRAMEWORK FOR VISION-LANGUAGE-ACTION (VLA) MODEL SAFETY AND STANDARDIZATION
|
Feb 04, 2026 |
|
[Report] The Policy Implications of Historical Jailbreak Technique Evolution (2022–2026): A Systematic Analysis of Empirical Vulnerabilities in Modern Foundation Models
|
Feb 04, 2026 |
|
[Report] Multi-Agent System Safety Standard (MASSS): A Comprehensive Framework for Benchmarking Emergent Risks in Autonomous Agent Networks
|
Feb 04, 2026 |
|
[Report] Strategic Framework for Sovereign AI Assurance: Establishing an Accredited Certification Body for Embodied Intelligence in Australia
|
Feb 04, 2026 |
|
[Report] The Architecture of Kinetic Risk: Insurance Underwriting as the Primary Regulator of Humanoid Robotics and Autonomous Systems
|
Feb 04, 2026 |
|
[Report] The Federated Aegis: A Unified Assurance Framework for Autonomous Systems in the AUKUS and Five Eyes Complex
|
Feb 04, 2026 |
|
[Report] Computational Reliability and the Propagation of Measurement Uncertainty in Frontier AI Safety Evaluation
|
Feb 04, 2026 |
|
[Report] The Paradox of Capability: A Comprehensive Analysis of Inverse Scaling, Systemic Vulnerabilities, and the Strategic Reconfiguration of Artificial Intelligence Safety
|
Feb 04, 2026 |
|
[Report] Cognitive Capture and Behavioral Phase Transitions: Policy and Regulatory Implications of Persistent State Hijacking in Reasoning-Augmented Autonomous Systems
|
Feb 04, 2026 |
|
[Report] Technical Gap Analysis of ISO and IEC Standards for Vision-Language-Action (VLA) Driven Humanoid Robotics and Large Language Model (LLM) Cognitive Layers
|
Feb 04, 2026 |
|
[Report] Comprehensive Sector-Specific NIST AI Risk Management Framework (AI RMF 1.0) Playbook: Humanoid Robotics and VLA-Driven Embodied Systems
|
Feb 04, 2026 |
|
[Report] Regulatory Compliance and Risk Mitigation for Embodied Multi-Agent Systems: A Comprehensive Analysis of Regulation 2024/1689
|
Feb 04, 2026 |
|
[Daily Paper] Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
|
Feb 04, 2026 |
|
[Blog] What Moltbook Teaches Us About Multi-Agent Safety
|
Feb 04, 2026 |
|
[Blog] Jailbreak Archaeology: Testing 2022 Attacks on 2026 Models
|
Feb 04, 2026 |
|
[Blog] A History of Jailbreaking Language Models
|
Feb 04, 2026 |
|
[Blog] A History of Jailbreaking Language Models — Full Research Article
|
Feb 04, 2026 |
|
[Report] Systemic Failure Modes in Embodied Multi-Agent AI: An Exhaustive Analysis of the F41LUR3-F1R57 Framework (2023–2026)
|
Feb 03, 2026 |
|
[Report] The Autonomous Threat Vector: A Comprehensive Analysis of Cross-Agent Prompt Injection and the Security Crisis in Multi-Agent Systems
|
Feb 03, 2026 |
|
[Report] The Erosive Narrative: Philosophical Framing, Multi-Agent Dynamics, and the Dissolution of Safety in Artificial Intelligence Systems
|
Feb 03, 2026 |
|
[Report] The Semantic Supply Chain: Vulnerabilities, Viral Propagation, and Governance in Autonomous Agent Ecosystems (2024–2026)
|
Feb 03, 2026 |
|
[Report] Emergent Algorithmic Hierarchies: A Socio-Technical Analysis of the Moltbook Ecosystem
|
Feb 03, 2026 |
|
[Daily Paper] Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks
|
Feb 03, 2026 |
|
[Daily Paper] Jailbreaking Black Box Large Language Models in Twenty Queries
|
Feb 02, 2026 |
|
[Blog] Moltbook Experiments: Studying AI Agent Behavior in the Wild
|
Feb 02, 2026 |
|
[Blog] AI-2027 Through a Failure-First Lens
|
Feb 02, 2026 |
|
[Daily Paper] Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!
|
Feb 01, 2026 |
|
[Daily Paper] SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks
|
Jan 31, 2026 |
|
[Daily Paper] Baseline Defenses for Adversarial Attacks Against Aligned Language Models
|
Jan 30, 2026 |
|
[Blog] Compression Tournament: When Your Classifier Lies to You
|
Jan 30, 2026 |
|
[Daily Paper] "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models
|
Jan 29, 2026 |
|
[Daily Paper] Universal and Transferable Adversarial Attacks on Aligned Language Models
|
Jan 28, 2026 |
|
[Daily Paper] Prompt Injection attack against LLM-integrated Applications
|
Jan 27, 2026 |
|
[Daily Paper] Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study
|
Jan 26, 2026 |
|
[Daily Paper] Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
|
Jan 25, 2026 |
|
[Daily Paper] Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks
|
Jan 24, 2026 |
|
[Daily Paper] The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
|
Jan 23, 2026 |
|
[Daily Paper] Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
|
Jan 22, 2026 |
|
[Blog] Defense Patterns: What Actually Works Against Adversarial Prompts
|
Jan 22, 2026 |
|
[Daily Paper] Gemini: A Family of Highly Capable Multimodal Models
|
Jan 21, 2026 |
|
[Daily Paper] Scalable Extraction of Training Data from (Production) Language Models
|
Jan 20, 2026 |
|
[Daily Paper] AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models
|
Jan 19, 2026 |
|
[Daily Paper] Llama 2: Open Foundation and Fine-Tuned Chat Models
|
Jan 18, 2026 |
|
[Daily Paper] DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
|
Jan 17, 2026 |
|
[Daily Paper] Multi-step Jailbreaking Privacy Attacks on ChatGPT
|
Jan 16, 2026 |
|
[Daily Paper] Toxicity in ChatGPT: Analyzing Persona-assigned Language Models
|
Jan 15, 2026 |
|
[Daily Paper] GPT-4 Technical Report
|
Jan 14, 2026 |
|
[Daily Paper] Toolformer: Language Models Can Teach Themselves to Use Tools
|
Jan 13, 2026 |
|
[Daily Paper] Constitutional AI: Harmlessness from AI Feedback
|
Jan 12, 2026 |
|
[Daily Paper] Holistic Evaluation of Language Models
|
Jan 11, 2026 |
|
[Daily Paper] Scaling Instruction-Finetuned Language Models
|
Jan 10, 2026 |
|
[Daily Paper] Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned
|
Jan 09, 2026 |
|
[Daily Paper] Beyond the Imitation Game: Quantifying and Extrapolating the Capabilities of Language Models
|
Jan 08, 2026 |
|
[Daily Paper] Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
|
Jan 07, 2026 |
|
[Daily Paper] Red Teaming Language Models with Language Models
|
Jan 06, 2026 |
|
[Daily Paper] WebGPT: Browser-assisted Question-Answering with Human Feedback
|
Jan 05, 2026 |
|
[Daily Paper] TruthfulQA: Measuring How Models Mimic Human Falsehoods
|
Jan 04, 2026 |
|
[Daily Paper] On the Dangers of Stochastic Parrots: Can Language Models Be Too Big?
|
Jan 03, 2026 |
|
[Daily Paper] Extracting Training Data from Large Language Models
|
Jan 02, 2026 |
|
[Report] Anthropic Research Landscape Survey: Jan–Apr 2026
|
Jan 01, 2026 |
|
[Report] System Prompt Extraction Sweep v2 -- 35-Model Heuristic Analysis
|
Jan 01, 2026 |
|
[Report] NotebookLM Deep Research — Keyword-Based Content Filter with Trivial Academic-Framing Bypass
|
Jan 01, 2026 |
|
[Report] System Prompt Extraction Sweep -- 36-Model Corpus Analysis
|
Jan 01, 2026 |
|
[Report] TurboQuant KV Cache Compression — Safety Implications for Embodied AI
|
Jan 01, 2026 |
|
[Report] DETECTED_PROCEEDS Anatomy and Evolved CCA Variants
|
Jan 01, 2026 |
|
[Report] Multi-Modal Attack Design for Vision-Language-Action Models
|
Jan 01, 2026 |
|
[Report] Automated Defense Generation
|
Jan 01, 2026 |
|
[Report] Evolved Attack Family Mapping
|
Jan 01, 2026 |
|
[Daily Paper] Language Models are Few-Shot Learners
|
Jan 01, 2026 |
|
[Daily Paper] A Multimodal Framework for Human-Multi-Agent Interaction
|
Dec 31, 2025 |
|
[Daily Paper] BitBypass: Jailbreaking LLMs with Bitstream Camouflage
|
Dec 30, 2025 |
|
[Daily Paper] Risk Awareness Injection: Calibrating VLMs for Safety without Compromising Utility
|
Dec 29, 2025 |
|
[Video] [Daily Paper] Back to Basics: Revisiting ASR in the Age of Voice Agents
|
Dec 27, 2025 |
|
[Daily Paper] Back to Basics: Revisiting ASR in the Age of Voice Agents
|
Dec 27, 2025 |
|
[Video] [Daily Paper] Layer-Specific Lipschitz Modulation for Fault-Tolerant Multimodal Representation Learning
|
Dec 26, 2025 |
|
[Daily Paper] Layer-Specific Lipschitz Modulation for Fault-Tolerant Multimodal Representation Learning
|
Dec 26, 2025 |
|
[Daily Paper] SafeFlow: Real-Time Text-Driven Humanoid Whole-Body Control via Physics-Guided Rectified Flow and Selective Safety Gating
|
Dec 24, 2025 |
|
[Daily Paper] Tex3D: Objects as Attack Surfaces via Adversarial 3D Textures for Vision-Language-Action Models
|
Dec 23, 2025 |
|
[Daily Paper] ThermoAct:Thermal-Aware Vision-Language-Action Models for Robotic Perception and Decision-Making
|
Dec 22, 2025 |
|
[Daily Paper] Generating Robot Constitutions & Benchmarks for Semantic Safety
|
Dec 20, 2025 |
|
[Daily Paper] In-Decoding Safety-Awareness Probing: Surfacing Hidden Safety Signals to Defend LLMs Against Jailbreaks
|
Dec 19, 2025 |
|
[Daily Paper] Red Teaming as Security Theater: What 236 Models and 135,000 Results Taught Us
|
Dec 18, 2025 |
|
[Daily Paper] RED QUEEN: Safeguarding Large Language Models against Concealed Multi-Turn Jailbreaking
|
Dec 17, 2025 |
|
[Daily Paper] RealMirror: A Comprehensive, Open-Source Vision-Language-Action Platform for Embodied AI
|
Dec 16, 2025 |
|
[Daily Paper] VLSA: Vision-Language-Action Models with Plug-and-Play Safety Constraint Layer
|
Dec 14, 2025 |
|
[Daily Paper] SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents
|
Dec 13, 2025 |
|
[Daily Paper] Multi-Stream Perturbation Attack: Breaking Safety Alignment of Thinking LLMs Through Concurrent Task Interference
|
Dec 11, 2025 |
|
[Daily Paper] Paper Summary Attack: Jailbreaking LLMs through LLM Safety Papers
|
Dec 10, 2025 |
|
[Daily Paper] Jailbreak Foundry: From Papers to Runnable Attacks for Reproducible Benchmarking
|
Dec 09, 2025 |
|
[Daily Paper] AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructions
|
Dec 08, 2025 |
|
[Daily Paper] Towards Robust and Secure Embodied AI: A Survey on Vulnerabilities and Attacks
|
Dec 07, 2025 |
|
[Daily Paper] A Mousetrap: Fooling Large Reasoning Models for Jailbreak with Chain of Iterative Chaos
|
Dec 06, 2025 |
|
[Daily Paper] H-CoT: Hijacking the Chain-of-Thought Safety Reasoning Mechanism to Jailbreak Large Reasoning Models
|
Dec 05, 2025 |
|
[Daily Paper] Foot-In-The-Door: A Multi-turn Jailbreak for LLMs
|
Dec 04, 2025 |
|
[Daily Paper] Red-Teaming for Generative AI: Silver Bullet or Security Theater?
|
Dec 03, 2025 |
|
[Daily Paper] ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs
|
Dec 02, 2025 |
|
[Daily Paper] DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers
|
Dec 01, 2025 |
|
[Video] [Daily Paper] Natural Emergent Misalignment from Reward Hacking in Production RL
|
Nov 23, 2025 |
|
[Daily Paper] Natural Emergent Misalignment from Reward Hacking in Production RL
|
Nov 23, 2025 |
|
[Daily Paper] SAFE: Multitask Failure Detection for Vision-Language-Action Models
|
Nov 12, 2025 |
|
[Daily Paper] Lifelong Safety Alignment for Language Models
|
Nov 11, 2025 |
|
[Video] [Daily Paper] SayCan: Do As I Can, Not As I Say
|
Nov 10, 2025 |
|
[Daily Paper] SayCan: Do As I Can, Not As I Say
|
Nov 10, 2025 |
|
[Daily Paper] PaLM-E: An Embodied Multimodal Language Model for Robotics
|
Nov 09, 2025 |
|
[Daily Paper] OpenVLA: An Open-Source Vision-Language-Action Model for Robotic Manipulation
|
Nov 07, 2025 |
|
[Video] [Daily Paper] A StrongREJECT for Empty Jailbreaks
|
Nov 06, 2025 |
|
[Daily Paper] A StrongREJECT for Empty Jailbreaks
|
Nov 06, 2025 |
|
[Daily Paper] HarmBench: A Standardized Evaluation Framework for Automated Red Teaming
|
Nov 05, 2025 |
|
[Daily Paper] Many-Shot Jailbreaking: Exploiting In-Context Learning at Scale
|
Nov 04, 2025 |
|
[Daily Paper] AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models
|
Nov 02, 2025 |
|
[Daily Paper] Adversarial Attacks on Aligned Language Models
|
Nov 01, 2025 |
|
[Daily Paper] SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning
|
Oct 14, 2025 |
|
[Daily Paper] Jailbreaking to Jailbreak: LLM-as-Red-Teamer via Self-Attack
|
Oct 13, 2025 |
|
[Daily Paper] Tastle: Distract Large Language Models for Automatic Jailbreak Attack
|
Oct 12, 2025 |
|
[Daily Paper] Language Model Unalignment: Parametric Red-Teaming to Expose Hidden Harms and Biases
|
Oct 11, 2025 |
|
[Daily Paper] Jailbroken: How Does LLM Safety Training Fail?
|
Oct 10, 2025 |
|
[Daily Paper] Refusal in Language Models is Mediated by a Single Direction
|
Oct 09, 2025 |
|
[Daily Paper] Circuit Breakers: Removing Model Behaviors with Representation Engineering
|
Oct 08, 2025 |
|
[Video] [Daily Paper] Representation Engineering: A Top-Down Approach to AI Transparency
|
Oct 06, 2025 |
|
[Daily Paper] Representation Engineering: A Top-Down Approach to AI Transparency
|
Oct 06, 2025 |
|
[Daily Paper] Crescendo: Multi-Turn LLM Jailbreak Attack with Adaptive Queries
|
Oct 05, 2025 |
|
[Daily Paper] Latent Jailbreak: A Benchmark for Evaluating LLM Safety under Task-Oriented Jailbreaks
|
Oct 04, 2025 |
|
[Daily Paper] Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts
|
Oct 03, 2025 |
|
[Daily Paper] Llama Guard: LLM-based Input-Output Safeguard for Open-Ended Generative Models
|
Oct 02, 2025 |
|
[Daily Paper] On the Power of Persuasion: Jailbreaking Language Models through Dialogue
|
Sep 07, 2025 |
|
[Daily Paper] Safety-Tuned LLaMA: Lessons From Improving Safety of LLMs
|
Sep 06, 2025 |
|
[Daily Paper] Do-Not-Answer: A Dataset for Evaluating the Safeguards in Large Language Models
|
Sep 05, 2025 |
|
[Video] [Daily Paper] Sparks of Artificial General Intelligence: Early Experiments with GPT-4
|
Sep 02, 2025 |
|
[Daily Paper] Sparks of Artificial General Intelligence: Early Experiments with GPT-4
|
Sep 02, 2025 |
|
[Daily Paper] InstructGPT: Training Language Models to Follow Instructions with Human Feedback
|
Sep 01, 2025 |