发表机构
State Key Laboratory of Media Convergence and Communication, Communication University of China（媒体融合与传播国家重点实验室，中国传媒大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对LLM智能体在长期社交关系中的隐私披露问题，提出EP-Mem弹性隐私记忆架构，通过用户策略驱动的令牌级记忆和隐私引擎边车实现边界控制，在EP-Bench基准上隐私分类准确率达94%，泄露减少75.6%。
AI 中文摘要
大型语言模型（LLM）智能体在充当人-智能体-人通信中的代表时面临严重的隐私风险。为防止此类泄露，智能体必须理解用户的社交关系，并遵守依赖上下文的社交信息披露边界。当前关于智能体记忆隐私的研究集中于瞬时交互，长期关系披露问题尚未得到探索。本文提出EP-Mem，一种弹性隐私记忆架构，将隐私重新定义为用户拥有的跨社交角色的边界控制。EP-Mem引入（1）由用户可配置的隐私策略驱动的令牌级记忆，该策略对人物和事件进行分层，结合领域级默认传播规则与事实级白名单/黑名单例外；（2）一个可插拔的边车组件，内含隐私引擎，在摘要、细节和边界粒度上使披露控制与记忆对齐，并在生成、存储和检索过程中强制执行。我们构建了EP-Bench，据我们所知，这是第一个具有跨会话关联事件的长期多方基准，用于策略条件的关系披露。实验表明，EP-Mem实现了94.0%的隐私分类准确率，将披露许可判断从22%提升至68%，并将隐私泄露减少75.6%，同时保持了检索性能和跨基准泛化能力。
英文摘要
Large language model (LLM) agents face critical privacy risks when acting as delegates in human-agent-human communication. To prevent such breaches, agents must understand users' social relationships and adhere to context-dependent social information disclosure boundaries. Current studies on agent memory privacy focus on instantaneous interactions, leaving the long-term relational disclosure problem unexplored. In this paper, we propose EP-Mem, an Elastic Privacy Memory architecture that reframes privacy as user-owned boundary control across social roles. EP-Mem introduces (1) token-level memory driven by user-configurable a privacy policy that stratifies persons and events, combining domain-level default circulation rules with fact-level whitelist/blacklist exceptions; and (2) a pluggable sidecar with a privacy engine that aligns disclosure controls with memory across summary, detail, and boundary granularities, enforced throughout generation, storage, and retrieval. We construct EP-Bench, to our knowledge the first long-term multi-party benchmark with cross-session correlated events for policy-conditioned relational disclosure. Experiments show that EP-Mem achieves 94.0% privacy classification accuracy, improves disclosure-permission judgment from 22% to 68%, and reduces privacy leakage by 75.6%, while maintaining retrieval performance and cross-benchmark generalization.
