EMBGuard introduces a novel, MLLM-based safety guardrail that explicitly identifies and explains physical hazards from (visual observation, action) pairs, enabling safer planning for embodied agents.

The paper proposes a novel attack paradigm demonstrating how compromising a single robot in an LLM-controlled multi-robot system can rapidly propagate malicious intent to cause coordinated unsafe acti…

This paper surveys the risks associated with world models, proposing a unified threat model and demonstrating adversarial attacks that show world models require rigorous safety standards comparable to…

The paper introduces RoboJailBench, the first standardized evaluation framework for assessing adversarial jailbreak attacks and defenses in embodied AI systems like robots.

The paper provides a holistic threat model for LLM-enabled robotic systems by analyzing how conventional, adversarial, and conversational threats propagate across the entire perception-planning-actuat…

The paper demonstrates a semantic denial-of-service attack against LLM-controlled robots by injecting short, safety-plausible phrases into the audio channel, causing the robot to halt or disrupt execu…

The paper proposes an algorithmic method using conformal prediction to formally certify high-probability safety for Belief-Space Neural Safety Filters (BeliefSF), significantly improving safety guaran…

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 introduces RUBAS, a rubric-based reinforcement learning framework that improves agent safety by providing fine-grained, multi-dimensional rewards for complex tool-use 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…

This paper systematically maps the expanded attack surface of agentic AI systems, identifying new threat vectors like RAG poisoning and cross-agent manipulation, and proposes a comprehensive security…

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…

This paper provides a comparative framework analyzing the distinct security and privacy risks inherent in virtual and robotic assistive systems, culminating in design recommendations for trustworthy t…

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

This survey provides a comprehensive, practical guide to ensuring the trustworthiness of complex, autonomous agentic AI systems by focusing on safety, robustness, privacy, and system security.

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…

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 argues that for embodied AI to be safe and effective, world models must be physically viable, requiring a structural shift from mere observation prediction to representing the underlying phy…

This paper addresses the critical need for trustworthy LLMs in science by proposing a comprehensive, multi-layered defense framework and methodology to evaluate unique scientific vulnerabilities.