PrivacyPeek: Auditing What LLM-Based Agents Acquire, Not Just What They Say
- 类型:arxiv
- 标识:2606.00152
- 链接:https://arxiv.org/abs/2606.00152
- 主分类:agent
- 形态:benchmark
- 被引:5
- 被引来源:Semantic Scholar
- S2被引:5
- OpenAlex被引:0
- 影响力被引:2
- TLDR:The experiments show that the unnecessary acquisition of sensitive information is widespread, and a correlation between the task-completion capability and acquisition-stage leakage, and auditing acquisition-stage privacy both urgent and necessary is observed.
- OpenAlex ID:W7163178005
- OpenAlex DOI:10.48550/arxiv.2606.00152
- DOI:10.48550/arxiv.2606.00152
- DOI来源:OpenAlex
- 开放获取:green
- 开放获取链接:https://doi.org/10.48550/arxiv.2606.00152
- OpenAlex更新:2026-09-06
- 副分类:evaluation
- 待LLM分类:否
- 标题中文:PrivacyPeek:审计 LLM Agent 获取了什么,而不仅仅是说了什么
- TLDR中文:实验表明,对敏感信息的不必要获取广泛存在,并观察到任务完成能力与获取阶段泄露之间的相关性,因此对获取阶段隐私进行审计既紧迫也必要。
- 来源文件:
- /inbox/tom/_candidates/2026-08-10-agent-rag-longcontext-candidates.json
- [S2 enrich]
- [OpenAlex backfill]