paperAugust 2026UnreviewedOpen access

A Comparative Survey of Security Risks in AI Systems: From LLMs to AI Agents and Embodied Agents

Baiqi Wu, Qing-Ming Li, Chun-Yi Zhou, Ting Wang, Shoulin Ji

ACM Computing Surveys

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 framew

Framework mappings

OWASP Top 10 for LLM Applications

LLM02Sensitive Information Disclosure

MITRE ATLAS

AML.T0024.000Infer Training Data Membership

Suggested from the entry's categories.

Cite

@article{wu2026comparative,
  title = {{A Comparative Survey of Security Risks in AI Systems: From LLMs to AI Agents and Embodied Agents}},
  author = {Baiqi Wu and Qing-Ming Li and Chun-Yi Zhou and Ting Wang and Shoulin Ji},
  year = {2026},
  month = aug,
  journal = {ACM Computing Surveys},
  doi = {10.1145/3837083},
  url = {https://www.semanticscholar.org/paper/6f3e92cf87e0f99a22425e710009a51958baf627}
}