Metraipolis › archive › dc_cc94ce842a82

SoK: Rethinking Jailbreaking in the Era of Agentic AI: Attacks, Defenses, and Practical Consideration — arXiv:2609.12413

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.12413
License (as archived)
CC0-1.0
Archived
2026-10-16T03:02:44.739Z
SHA-256 of the archived text
a367ae7f0065e7c40d9b6569eab3e16ca436634f7e57b78242a027c1e549b10e
Stable URL of this page
https://metraipolis.com/documento/dc_cc94ce842a82

How to cite

SoK: Rethinking Jailbreaking in the Era of Agentic AI: Attacks, Defenses, and Practical Consideration — arXiv:2609.12413 — arXiv (en), https://arxiv.org/abs/2609.12413 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cc94ce842a82 (Metraipolis archive dc_cc94ce842a82, sha256 a367ae7f0065e7c40d9b6569eab3e16ca436634f7e57b78242a027c1e549b10e)
BibTeX
@misc{dccc94ce842a82,
  title = {SoK: Rethinking Jailbreaking in the Era of Agentic AI: Attacks, Defenses, and Practical Consideration — arXiv:2609.12413},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.12413},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cc94ce842a82; sha256 a367ae7f0065e7c40d9b6569eab3e16ca436634f7e57b78242a027c1e549b10e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12413. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 findings remain valid in the era of modern LLMs and agentic AI?} We address this question through a Systematization of Knowledge (SoK) that reframes jailbreak security around the full agentic execution pipeline. We develop unified taxonomies of attacks and defenses spanning user interaction, planning and reasoning, memory, tool use, and inter-agent communication, and introduce a security--utility--efficiency evaluation framework that separates native harmful-prompt safety, adversarial jailbreak robustness, and agent-level security outcomes. We further conduct a controlled empirical study of representative attacks and defenses within a common agentic framework. Our results reveal three important gaps. First, strong native alignment does not imply robustness to adversarial jailbreaks. Second, defense effectiveness is highly model-, attack-, and component-dependent and can come at substantial cost in over-refusal, utility, and latency. Third, low final-response attack success can mask severe intermediate compromise: planning, memory, and tool interactions may remain unsafe even when the final response is successfully filtered. These findings motivate a shift from response-centric jailbreak defense toward cross-layer, execution-aware security that protects agent state, component transitions, and external actions while preserving practical utility and efficiency.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.12413 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T02:51:27.791Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).