研究人员正在开发新方法来保护用户在使用大型语言模型 (LLM) 和 AI 代理时的隐私。几篇论文介绍了用于审计和缓解隐私风险的基准和框架，重点关注代理如何获取和潜在地滥用敏感信息。这些方法旨在确保 LLM 只访问必要数据，并抵御复杂的重识别攻击，即使在结合零散线索和公开信息时也是如此。 AI
影响 这些进展对于通过解决关键隐私问题来建立信任和实现 LLM 代理的更广泛采用至关重要。
排序理由 多篇在 arXiv 上发表的学术论文介绍了用于 LLM 隐私的新基准和框架。
AI 生成摘要 · Google Gemini · 来自 6 个来源。 我们如何撰写摘要 →
arXiv:2606.04067v1 Announce Type: cross Abstract: As LLMs become increasingly woven into everyday workflows, user queries sent to cloud hosted LLMs routinely mix task-essential content with task non-essential sensitive disclosures, yet type based PII redaction is context agnostic…
arXiv:2606.04903v1 Announce Type: cross Abstract: We introduce the LLM agent architecture Agentic Redux, intended for use with nontrivial problem domains that require linear auditability. Using the typed lambda calculus, we prove that, run on appropriate domains, Agentic Redux ex…
We introduce the LLM agent architecture Agentic Redux, intended for use with nontrivial problem domains that require linear auditability. Using the typed lambda calculus, we prove that, run on appropriate domains, Agentic Redux executions are semantically guaranteed to be correct…
arXiv:2606.00152v1 Announce Type: cross Abstract: LLM-based agents are rapidly advancing, autonomously invoking external tools to complete multi-step tasks for users. However, agents often acquire more sensitive information than the task requires. Existing privacy benchmarks audi…
arXiv:2603.18382v2 Announce Type: replace Abstract: Anonymization is often assumed to protect privacy once explicit identifiers are removed, because re-identification has historically required specialized expertise, tailored algorithms, and manual corroboration. We show that LLM-…
arXiv:2605.30848v1 Announce Type: cross Abstract: Agentic LLMs with web search change the threat model for text anonymization: weak contextual cues can become cross-referenceable evidence for re-identification, yet those same details also carry downstream analytic value of the te…