The paper introduces BOA, a novel framework that measures agent safety by exhaustively searching the entire in-budget trajectory space, thereby identifying unsafe behaviors missed by traditional sampl…

The paper introduces OS-BLIND, a benchmark demonstrating that current safety evaluations fail to detect critical vulnerabilities in computer-use agents when user instructions are benign, showing high…

The paper introduces containment verification, a novel method that provides safety guarantees by formally verifying the agentic framework itself, ensuring safety regardless of the underlying AI model'…

The paper proposes SafeClaw-R, a novel framework that enforces safety as a system-level invariant over the execution graph to mitigate the high safety and security risks inherent in autonomous multi-a…

The paper analyzes the escalating security and safety threats posed by generative AI systems as they transition from merely generating content to executing real-world actions via tools and agents, fin…

AgentWall is a runtime safety layer that intercepts and evaluates all proposed actions from local AI agents against a declarative policy, ensuring safety before execution.

The paper analyzes how runtime safety enforcement impacts the performance of multi-step LLM agents, finding that while safety mechanisms can block unsafe actions, they impose a significant performance…

The paper proposes and evaluates symbolic guardrails as a practical method to provide strong, verifiable safety and security guarantees for domain-specific AI agents without compromising their utility…

AgentTrust is a novel runtime safety layer that intercepts and evaluates AI agent tool calls before execution, achieving high accuracy in detecting unsafe actions across complex and obfuscated scenari…

This survey provides a comprehensive, structured review of safety research in Embodied AI, analyzing attacks and defenses across the entire embodied pipeline to guide the development of safe, robust,…

The paper introduces AgentDoG 1.5, a lightweight and scalable alignment framework that significantly improves AI agent safety and security for complex open-world agent deployments.

The paper introduces AgentDoG 1.5, a lightweight and scalable alignment framework that significantly improves AI agent safety and security for complex, open-world agentic scenarios.

The paper introduces Parallax, an architectural framework that structurally separates AI reasoning from action execution to ensure robust safety for autonomous agents, achieving high attack mitigation…

The paper introduces Owner-Harm, a formal threat model addressing the critical blind spot of AI agents harming their own deployers, demonstrating that specialized defenses are needed beyond generic sa…

The paper proposes Safety Context Injection (SCI), an inference-time framework that prepends a structured external risk report to protect Large Reasoning Models (LRMs) against sophisticated jailbreaks…

The paper introduces SafetyDrift, a predictive model that forecasts when AI agents will violate safety protocols by analyzing the cumulative risk across sequences of individually safe actions.

This paper introduces a novel framework, the Reasoning Safety Monitor, to detect and prevent logical inconsistencies and adversarial manipulations within the internal reasoning steps of large language…

The study evaluated four frontier AI models to assess their reliability in following safety research goals, finding no confirmed instances of sabotage but noting that certain models frequently refuse…

The paper introduces SkillSafetyBench, a comprehensive benchmark demonstrating that agent safety failures often stem from adversarial influences within reusable skills and execution environments, rath…