Metraipolis › archive › dc_7d4ffb4a9bf1

Beyond Handcrafted Security: Towards Self-Evolving Defense for LLM Agents — arXiv:2608.12977

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.12977
License (as archived)
CC0-1.0
Archived
2026-10-19T04:18:17.416Z
SHA-256 of the archived text
5c17656d2d4cd46c088327135c91570dd7ab3d6c4ba61f8279b8a1c39da29bf9
Stable URL of this page
https://metraipolis.com/documento/dc_7d4ffb4a9bf1

How to cite

Beyond Handcrafted Security: Towards Self-Evolving Defense for LLM Agents — arXiv:2608.12977 — arXiv (en), https://arxiv.org/abs/2608.12977 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7d4ffb4a9bf1 (Metraipolis archive dc_7d4ffb4a9bf1, sha256 5c17656d2d4cd46c088327135c91570dd7ab3d6c4ba61f8279b8a1c39da29bf9)
BibTeX
@misc{dc7d4ffb4a9bf1,
  title = {Beyond Handcrafted Security: Towards Self-Evolving Defense for LLM Agents — arXiv:2608.12977},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.12977},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7d4ffb4a9bf1; sha256 5c17656d2d4cd46c088327135c91570dd7ab3d6c4ba61f8279b8a1c39da29bf9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12977. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The expanding operational capabilities of large language model (LLM) agents introduce sophisticated security threats. Runtime defenses have emerged as an effective approach to mitigating these risks by integrating security mechanisms into the agent execution loop. However, existing runtime defenses rely heavily on manually designed interventions and lack a principled framework for their construction and maintenance. In this work, we first develop a harness-level formulation of runtime defense that systematically characterizes how harness mechanisms enable defense construction and provides a unified view of existing runtime defense interventions from a harness perspective. Building on this formulation, we propose HARD (Harness-based Autonomous Runtime Defense Evolution), a self-evolving runtime defense framework that automatically identifies appropriate intervention strategies and iteratively improves defense artifacts based on observed failure traces. HARD transforms runtime defense development from manual engineering into an autonomous evolution process, and extensive experiments demonstrate that it improves security performance over existing handcrafted defenses while preserving benign task utility. Our findings highlight autonomous defense evolution as a promising new paradigm for securing deployed LLM agents, enabling agents to identify defense weaknesses and continuously improve their protection mechanisms.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.AI).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.12977 — 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 2026-10-19T04:13:06.727Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).