Safety-Aware Zero Trust Enforcement for IoT and Cyber-Physical Systems
Introducing MentalHealthBench
8 min
Control-Token Injection Suppresses Chain-of-Thought and Defeats Reasoning-Based Oversight in Tool-Using Agents
SSP-Bench: A Hybrid Data Generation Framework for Safety, Security, and Privacy Evaluation
Import AI 473: The US's superintelligence strategy; human brain in a mouse skull; and machine hermeneutics
15 min
Worst-Case Hidden-Vehicle Trajectory Search in Spatiotemporal Occlusion Regions
Collective Loss of Control in LLM Agent Systems: An Epidemic Account of Mutation, Contagion, and Recovery
Inoculation Midtraining with Learned Neologisms
ReactHuman: A Physics-Grounded Benchmark for Human-Like Reactive Decision-Making in Embodied Multimodal LLMs
Recognition-Refusal Misalignment in LLMs: Why Models Answer Structurally Unanswerable Questions
OpenAI previews privacy-focused system for detecting AI misuse
2 min