SoK: Rethinking Jailbreaking in the Era of Agentic AI: Attacks, Defenses, and Practical Consideration

Abstract

Large language models (LLMs) are rapidly evolving from conversational assistants into agentic AI systems that reason, plan, invoke tools, maintain persistent memory, communicate with other agents, and execute multi-step tasks. At the same time, modern models exhibit substantially stronger native safety alignment than earlier generations on which many jailbreak attacks and defenses were originally studied. This shift raises a fundamental question: \textit{which established jailbreak-security find

Categories

Framework mappings

Suggested from the entry's categories.

@misc{mia2026sok,
  title = {{SoK: Rethinking Jailbreaking in the Era of Agentic AI: Attacks, Defenses, and Practical Consideration}},
  author = {Md. Jueal Mia and Yanzhao Wu and S. Uluagac and M. Amini},
  year = {2026},
  month = sep,
  eprint = {2609.12413},
  archivePrefix = {arXiv},
  url = {https://www.semanticscholar.org/paper/1664c9b5d52fbb43aa9582e97dc73096e344adc0}
}