Metraipolis › archive › dc_406969b98d2e

SecureGARD: Dynamic Ontology-Guided Governance for Secure Tool-Using LLM Agents — arXiv:2611.06682

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.06682
License (as archived)
CC0-1.0
Archived
2026-11-05T18:22:24.063Z
SHA-256 of the archived text
1909f4685712f0e04518fe110efe22ec2a3711b8f34d3e1a4732fdfe8210174b
Stable URL of this page
https://metraipolis.com/documento/dc_406969b98d2e

How to cite

SecureGARD: Dynamic Ontology-Guided Governance for Secure Tool-Using LLM Agents — arXiv:2611.06682 — arXiv (en), https://arxiv.org/abs/2611.06682 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_406969b98d2e (Metraipolis archive dc_406969b98d2e, sha256 1909f4685712f0e04518fe110efe22ec2a3711b8f34d3e1a4732fdfe8210174b)
BibTeX
@misc{dc406969b98d2e,
  title = {SecureGARD: Dynamic Ontology-Guided Governance for Secure Tool-Using LLM Agents — arXiv:2611.06682},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.06682},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_406969b98d2e; sha256 1909f4685712f0e04518fe110efe22ec2a3711b8f34d3e1a4732fdfe8210174b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06682. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Tool-using large language model (LLM) agents translate model outputs into consequential actions, turning indirect prompt injection into an execution-security problem. Existing defenses constrain tool calls, trajectories, or information flows, but often leave action semantics, state dependencies, and evidence relations implicit, limiting generalization across heterogeneous tools and complicating safe updates. We present \ours{}, a dynamic ontology-guided governance framework. \ours{} grounds heterogeneous calls in a shared semantic representation and combines an executable ontology with episode-level task state to derive deterministic ready, waiting, and forbidden decisions. A waiting decision identifies an unmet but recoverable obligation, enabling bounded replanning without expanding the agent's authorization boundary. \ours{} evolves its ontology offline from verified training executions. An offline LLM proposes instance-independent action--state axioms, which are accepted only if they address ontology errors exposed by training failures, preserve logical consistency and protected entailments, and pass held-out validation before the ontology is frozen. We evaluate \ours{} on AgentDojo, ASB, and AgentDyn under benign and indirect prompt-injection settings. \ours{} achieves a 0\% attack success rate (ASR) across all three benchmarks while improving task utility under attack compared with existing baselines. These results show that explicit semantic governance can strengthen execution security without indiscriminate blocking.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.06682 — 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 2026-11-05T18:15:49.023Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).