paperMarch 2026Unreviewed

The Attack and Defense Landscape of Agentic AI: A Comprehensive Survey

Juhee Kim, Xiaoyuan Liu, Zhun Wang, Shi Qiu, Bo Li, Wenbo Guo, Dawn Song

Abstract

AI agents that combine large language models with non-AI system components are rapidly emerging in real-world applications, offering unprecedented automation and flexibility. However, this unprecedented flexibility introduces complex security challenges fundamentally different from those in traditional software systems. This paper presents the first systematic and comprehensive survey of AI agent security, including an analysis of the design space, attack landscape, and defense mechanisms for se

Cite

@misc{kim2026attack,
  title = {{The Attack and Defense Landscape of Agentic AI: A Comprehensive Survey}},
  author = {Juhee Kim and Xiaoyuan Liu and Zhun Wang and Shi Qiu and Bo Li and Wenbo Guo and Dawn Song},
  year = {2026},
  month = mar,
  eprint = {2603.11088},
  archivePrefix = {arXiv},
  url = {https://www.semanticscholar.org/paper/94c189f236921d08c8709a8d27fd431b5c0a61ea}
}