Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses

• URL: http://arxiv.org/abs/2605.02900v1
• Date: Sat, 28 Mar 2026 13:21:44 GMT
• Title: Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses
• Abstract summary: Embodied Artificial Intelligence (Embodied AI) integrates perception, cognition, planning, and interaction into agents that operate in safety-critical environments.<n>Unlike digital AI systems, embodied agents must act under uncertain sensing, incomplete knowledge, and dynamic human-robot interactions.<n>This survey provides a comprehensive review of safety research in embodied AI, examining attacks and defenses across the full embodied pipeline.
• Score: 168.50301366360344
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Embodied Artificial Intelligence (Embodied AI) integrates perception, cognition, planning, and interaction into agents that operate in open-world, safety-critical environments. As these systems gain autonomy and enter domains such as transportation, healthcare, and industrial or assistive robotics, ensuring their safety becomes both technically challenging and socially indispensable. Unlike digital AI systems, embodied agents must act under uncertain sensing, incomplete knowledge, and dynamic human-robot interactions, where failures can directly lead to physical harm. This survey provides a comprehensive and structured review of safety research in embodied AI, examining attacks and defenses across the full embodied pipeline, from perception and cognition to planning, action and interaction, and agentic system. We introduce a multi-level taxonomy that unifies fragmented lines of work and connects embodied-specific safety findings with broader advances in vision, language, and multimodal foundation models. Our review synthesizes insights from over 400 papers spanning adversarial, backdoor, jailbreak, and hardware-level attacks; attack detection, safe training and robust inference; and risk-aware human-agent interaction. This analysis reveals several overlooked challenges, including the fragility of multimodal perception fusion, the instability of planning under jailbreak attacks, and the trustworthiness of human-agent interaction in open-ended scenarios. By organizing the field into a coherent framework and identifying critical research gaps, this survey provides a roadmap for building embodied agents that are not only capable and autonomous but also safe, robust, and reliable in real-world deployment.

Related papers

• Toward Secure AI-Powered Penetration Testing Agents: Security Threats, Guardrails, and Architectural Perspectives [0.0]
  LLM-powered autonomous agents are transforming the penetration testing space with dynamic, multi-step offensive security.<n>But the ability to have persistent memory, to take actions in the real world, and to do long-horizon reasoning raises qualitatively different security concerns.<n>Existing guardrail mechanisms for conversational AI may not be sufficient to secure autonomous AI pentesting agents accordingly.
  arXiv  Detail & Related papers  (2026-09-15T06:19:50Z)
• Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security [57.35851886874902]
  Agentic AI systems execute complex tasks autonomously, but their multi-step trajectories introduce new failure modes that challenge trustworthiness.<n>This survey provides a focused examination of trustworthy agentic AI through two core dimensions that are critical for high-risk deployments.<n>For each dimension, we clarify key concepts, identify where risks emerge along the agent workflow, and summarize stage-targeted mitigation strategies.
  arXiv  Detail & Related papers  (2026-05-17T10:26:37Z)
• Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms [61.29786895012393]
  Vision-Language-Action (VLA) models are emerging as a unified substrate for embodied intelligence.<n>This survey provides a unified and up-to-date overview of safety in Vision-Language-Action models.
  arXiv  Detail & Related papers  (2026-04-26T15:58:19Z)
• A Survey of Agentic AI and Cybersecurity: Challenges, Opportunities and Use-case Prototypes [7.02443431688472]
  Agentic AI marks an important transition from single-step generative models to systems capable of reasoning, planning, acting, and adapting over long-lasting tasks.<n>This survey examines the implications of agentic AI for cybersecurity.
  arXiv  Detail & Related papers  (2026-01-08T02:46:06Z)
• OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows [77.95511352806261]
  Computer-using agents powered by Vision-Language Models (VLMs) have demonstrated human-like capabilities in operating digital environments like mobile platforms.<n>We propose OS-Sentinel, a novel hybrid safety detection framework that combines a Formal Verifier for detecting explicit system-level violations with a Contextual Judge for assessing contextual risks and agent actions.
  arXiv  Detail & Related papers  (2025-10-28T13:22:39Z)
• ANNIE: Be Careful of Your Robots [48.89876809734855]
  We present the first systematic study of adversarial safety attacks on embodied AI systems.<n>We show attack success rates exceeding 50% across all safety categories.<n>Results expose a previously underexplored but highly consequential attack surface in embodied AI systems.
  arXiv  Detail & Related papers  (2025-09-03T15:00:28Z)
• Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents [0.0]
  Decentralized AI agents will soon interact across internet platforms, creating security challenges beyond traditional cybersecurity and AI safety frameworks.<n>We introduce textbfmulti-agent security, a new field dedicated to securing networks of decentralized AI agents against threats that emerge or amplify through their interactions.
  arXiv  Detail & Related papers  (2025-05-04T12:03:29Z)
• Towards Robust and Secure Embodied AI: A Survey on Vulnerabilities and Attacks [22.154001025679896]
  Embodied AI systems, including robots and autonomous vehicles, are increasingly integrated into real-world applications.<n>These vulnerabilities manifest through sensor spoofing, adversarial attacks, and failures in task and motion planning.
  arXiv  Detail & Related papers  (2025-02-18T03:38:07Z)
• Considerations Influencing Offense-Defense Dynamics From Artificial Intelligence [0.0]
  AI can enhance defensive capabilities but also presents avenues for malicious exploitation and large-scale societal harm.<n>This paper proposes a taxonomy to map and examine the key factors that influence whether AI systems predominantly pose threats or offer protective benefits to society.
  arXiv  Detail & Related papers  (2024-12-05T10:05:53Z)
• HAICOSYSTEM: An Ecosystem for Sandboxing Safety Risks in Human-AI Interactions [95.49509269498367]
  We present HAICOSYSTEM, a framework examining AI agent safety within diverse and complex social interactions.<n>We run 1840 simulations based on 92 scenarios across seven domains (e.g., healthcare, finance, education)<n>Our experiments show that state-of-the-art LLMs, both proprietary and open-sourced, exhibit safety risks in over 50% cases.
  arXiv  Detail & Related papers  (2024-09-24T19:47:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.