arXiv cs.AI· Yixiang Luo, Ziheng Ma, Ke Chang, Jian Wang, Jiqiang Liu·· 15 小时前AI 评分31
当安全检查变成隐私风险：面向 LLM 智能体安全审计的隐私保护范式
When Safety Checks Become Privacy Risks: A Privacy-Preserving Paradigm for LLM Agent Safety Auditing
AI 导读
研究者提出隐私保护安全审计范式，将委托审计计算与明文访问、执行权限分离，并落地为框架 SealCall，结合学习式审计表示、基于 CKKS 的加密相似度计算与绑定受审工具调用的执行控制。在 1,252 个公开二元候选上，SealCall 在分组嵌套评估下平均 F1 达 0.840，所有测量案例中审计决策与明文一致，代表性配置每次加密评分耗时 0.176 s。
正文 · 原文
Abstract: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.
| Comments: | 12 pages, 2 figures, 10 tables |
| Subjects: | Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.41401 [cs.CR] |
| (or arXiv:2610.41401v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2610.41401 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yixiang Luo [view email]
[v1]
Fri, 30 Oct 2026 08:12:45 UTC (2,264 KB)
来源：arXiv cs.AI · arxiv.org