Tag: agentic AI safety
Browse our exclusive articles!
Safe-SAIL: Fine-Grained Safety Analysis of Large Language Models
Discover Safe-SAIL, a framework using sparse autoencoders for detailed safety analysis and interpretability of large language models in critical domains.
Benchmarking Outcome-Driven Constraint Violations in AI Agents
Discover a new benchmark assessing outcome-driven constraint violations in autonomous AI agents to improve safety and ethical compliance under KPI pressure...
Ensuring Dataset Safety in Autonomous Driving AI
Explore key requirements, risks, and assurance strategies to ensure dataset safety in autonomous driving AI systems for reliable and secure performance.
ASGuard: Mitigating Jailbreaking in Large Language Models
ASGuard uses activation-scaling to prevent targeted jailbreaking attacks on LLMs, enhancing safety without compromising model utility or performance.
Parallax: Securing Autonomous AI Agents from Risks
Discover how Parallax protects AI agents by separating thinking from acting, blocking 99% of attacks and ensuring secure autonomous execution.