#AIOps
#Research
"Safety in Embodied AI:
A Survey of Risks, Attacks, and Defenses", Mar. 2026.
// 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. This 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
Post #2250
160
Forwarded from CyberSecurityTechnologies
Safety_in_Embodied_AI.pdf12.8 MB