Metraipolis › archive › dc_c8ae712e6eec

AgentAntibody: An Adaptive Immune System for Defending LLM Agents against Prompt Injection — arXiv:2608.04053

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.04053
License (as archived)
CC0-1.0
Archived
2026-10-31T11:13:29.312Z
SHA-256 of the archived text
d06eb5b7b48e5a4e4862dd410498004fbdd0458b4b53a3726dc95b46706976d2
Stable URL of this page
https://metraipolis.com/documento/dc_c8ae712e6eec

How to cite

AgentAntibody: An Adaptive Immune System for Defending LLM Agents against Prompt Injection — arXiv:2608.04053 — arXiv (en), https://arxiv.org/abs/2608.04053 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c8ae712e6eec (Metraipolis archive dc_c8ae712e6eec, sha256 d06eb5b7b48e5a4e4862dd410498004fbdd0458b4b53a3726dc95b46706976d2)
BibTeX
@misc{dcc8ae712e6eec,
  title = {AgentAntibody: An Adaptive Immune System for Defending LLM Agents against Prompt Injection — arXiv:2608.04053},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.04053},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c8ae712e6eec; sha256 d06eb5b7b48e5a4e4862dd410498004fbdd0458b4b53a3726dc95b46706976d2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04053. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Prompt injection remains a critical threat to LLM agents, yet existing defenses treat each task as a self-contained problem, independent of previous encounters. In practice, user requests are often underspecified: they describe the desired outcome without fully specifying acceptable behavior. An injection can exploit this ambiguity, causing the agent to complete the task in a way the user would reject. As the user's expectations become clearer through concrete cases, a defense should learn from each encounter and apply what it learns to the next. Inspired by adaptive immunity, we propose AgentAntibody, which equips LLM agents with a self-evolving immune system against prompt injection. AgentAntibody represents its evolving understanding of the user's security boundary as a persistent library of antibodies. At runtime, the library recognizes threats to this boundary and mounts corresponding immune responses. Across encounters, it evolves to strengthen the agent's immunity to future attacks. Extensive experiments across three benchmarks and four backbone LLMs show that, by learning the user's boundary through experience, AgentAntibody outperforms existing defenses in preventing harmful actions while preserving legitimate task completion, even when the harmful and legitimate actions are both compatible with the stated task.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.AI).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.04053 — 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 2026-10-31T11:02:13.470Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).