Aug 2026· ACM Computing Surveys· Vol 58, pp. 1 - 38· 3 citations· 190 references
TL;DR
This work presents a unified comparison of large language models, AI agents, and embodied agents, introducing a taxonomy of risks spanning data, models, systems, content, and applications, alongside a catalog of 24 specific threats.
Abstract
Rapid AI development across industries raises pressing security and privacy risks. This work presents a unified comparison of large language models, AI agents, and embodied agents, introducing a taxonomy of risks spanning data, models, systems, content, and applications, alongside a catalog of 24 specific threats. We contrast attack surfaces and methods across the three system types to reveal common patterns and distinctive vulnerabilities. We also survey mainstream AI security assessment frameworks and evaluate how relevant laws and regulations currently address these risks. Finally, we outline concrete directions for future research and practice aimed at building robust, secure agent ecosystems.
Embodied Artificial Intelligence (AI) introduces cyber–physical risks because digital failures and attacks can cause physical harm. This survey organizes embodied AI safety through a four-layer reference architecture — comprising the physical interaction, system and middleware, algorithm and decision, and cloud–edge an...
Tuo Feng, Yue Zhang, Shi-Ji Zhou et al.· AI Plus· 0 citations
Evidence concentrates on prompt/reasoning, memory, and tool-mediated attacks, predominantly in single-agent settings, within the selected studies, to guide more systematic, architecture-aware, and reproducible security evaluation of agentic AI.
Heewon Baek, Alsharif Abuadbba, Kristen Moore et al.· 0 citations
A formal framework for security in agentic AI is developed, built around an ideal predicate ϕ that decides, for a given ( prompt, context, result ) triple, whether the agent’s behaviour is acceptable.
F. Durak, Tadayoshi Kohno, Franziska Roesner· 0 citations
Several open research questions are identified, including how to efficiently record incidents and how to determine whether vulnerabilities and incidents generalize, and privacy requirements are summarized and research directions for the secure and trustworthy deployment of AI agents are outlined.
Anastasia Pustozerova, E. Bagdasarian, Luca Beurer-Kellner et al.· 0 citations
LLM-powered autonomous agents are transforming the penetration testing space with dynamic, multi-step offensive security workflows that require minimal supervision by humans. These agents leverage sophisticated reasoning abilities and external security tools to independently carry out reconnaissance, identify vulnerabi...
Y. RahulDevT, Hiran V. Nath· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
