English(EN) When Safety Checks Become Privacy Risks: A Privacy-Preserving Paradigm for LLM Agent Safety Auditing

新框架SealCall通过隐私保护增强LLM代理安全审计

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-03 05:00

研究人员开发了一个名为SealCall的新框架，以解决大型语言模型（LLM）代理安全审计中的隐私问题。所提出的范式将审计结果的计算与访问或执行敏感数据的权限分开。SealCall利用学习到的审计表示和加密计算技术（特别是CKKS）来保护用户信息免受外部审计员的侵害。在对公共数据的评估中，SealCall实现了0.840的平均F1分数，同时确保了明文审计决策的保留。 AI

影响增强了LLM代理安全审计中的隐私性，可能支持更敏感的应用。

排序理由这是一篇详细介绍新技术框架和方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 11 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是一篇详细介绍新技术框架和方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Yixiang Luo, Ziheng Ma, Ke Chang, Jian Wang, Jiqiang Liu · 2026-11-03 05:00

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

arXiv:2610.41401v1 Announce Type: cross 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 a…

本文如何被排名

报道来源 [1]

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

相关实体

相关话题