Metraipolis › archive › dc_161d21be58df

When Safety Checks Become Privacy Risks: A Privacy-Preserving Paradigm for LLM Agent Safety Auditing — arXiv:2610.41401

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41401
License (as archived): CC0-1.0
Archived: 2026-11-03T07:42:48.021Z
SHA-256 of the archived text: 0414737df3597f802bf3de839129150b5271a0eb320d42f62426315019dc1fa8
Stable URL of this page: https://metraipolis.com/documento/dc_161d21be58df

How to cite

When Safety Checks Become Privacy Risks: A Privacy-Preserving Paradigm for LLM Agent Safety Auditing — arXiv:2610.41401 — arXiv (en), https://arxiv.org/abs/2610.41401 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_161d21be58df (Metraipolis archive dc_161d21be58df, sha256 0414737df3597f802bf3de839129150b5271a0eb320d42f62426315019dc1fa8)

BibTeX

@misc{dc161d21be58df,
  title = {When Safety Checks Become Privacy Risks: A Privacy-Preserving Paradigm for LLM Agent Safety Auditing — arXiv:2610.41401},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41401},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_161d21be58df; sha256 0414737df3597f802bf3de839129150b5271a0eb320d42f62426315019dc1fa8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41401. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language model agents interact with online services through tool calls that may access private data or perform sensitive actions. Specialized providers can supply and maintain pre-execution safety auditing capabilities for agent operators. However, sending task descriptions, call arguments, and interaction histories to an external auditor may expose sensitive user information. In this work, we propose a paradigm for privacy-preserving safety auditing that separates delegated audit computation from plaintext access and execution authority. Grounded in a three-domain auditing model, the paradigm connects trusted representation construction, encrypted audit computation, and trusted decision and execution through explicit interfaces. These interfaces accommodate alternative representations and scorers, while encrypted computation protects audit inputs from a semi-honest auditor. We instantiate this paradigm in SealCall, a framework combining learned audit representations, CKKS-based encrypted similarity computation, and execution control bound to audited tool calls. Evaluated on 1,252 public binary candidates, SealCall achieves a mean F1 score of 0.840 under grouped nested evaluation, while preserving plaintext audit decisions in all measured cases. A representative configuration completes each encrypted scoring operation in 0.176 s.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.41401 — 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 2026-11-03T07:39:37.381Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).