MemPrivacy：面向边缘-云代理的隐私保护个性化内存管理

MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents

May 10, 2026

作者: Yining Chen, Jihao Zhao, Bo Tang, Haofen Wang, Feiyu Xiong, Zhiyu Li

cs.AI

摘要

随着基于大语言模型的智能体在边缘-云环境中日益普及，个性化记忆已成为实现长期适应用户中心交互的关键能力。然而，云辅助记忆管理会暴露敏感用户信息，现有隐私保护方法通常依赖激进式掩码处理，但这种方式会移除与任务相关的语义信息，进而降低记忆效用与个性化质量。为此，我们提出MemPrivacy方法：该方法在边缘设备上识别隐私敏感片段，使用语义化结构类型感知占位符替换后交由云端进行记忆处理，并在需要时于本地恢复原始值。通过将隐私保护与语义破坏相解耦，MemPrivacy在最小化敏感数据暴露的同时，保留了记忆形成与检索所需的关键信息。我们还构建了面向系统化评估的MemPrivacy基准测试集，该数据集涵盖200名用户、超过5.2万个隐私实例，并引入四级隐私分类体系以支持可配置的保护策略。实验结果表明，MemPrivacy在隐私信息提取任务中表现优异，显著超越GPT-5.2、Gemini-3.1-Pro等强大通用模型，同时推理延迟更低。在多个广泛使用的记忆系统中，MemPrivacy将效用损失控制在1.6%以内，优于基线掩码策略。总体而言，MemPrivacy为边缘-云智能体实现了隐私保护与个性化记忆效用的有效平衡，支持安全、实用且对用户透明的部署。

English

As LLM-powered agents are increasingly deployed in edge-cloud environments, personalized memory has become a key enabler of long-term adaptation and user-centric interaction. However, cloud-assisted memory management exposes sensitive user information, while existing privacy protection methods typically rely on aggressive masking that removes task-relevant semantics and consequently degrades memory utility and personalization quality. To address this challenge, We propose MemPrivacy, which identifies privacy-sensitive spans on edge devices, replaces them with semantically structured type-aware placeholders for cloud-side memory processing, and restores the original values locally when needed. By decoupling privacy protection from semantic destruction, MemPrivacy minimizes sensitive data exposure while retaining the information required for effective memory formation and retrieval. We also construct MemPrivacy-Bench for systematic evaluation, a dataset covering 200 users and over 52k privacy instances, and introduce a four-level privacy taxonomy for configurable protection policies. Experiments show that MemPrivacy achieves strong performance in privacy information extraction, substantially surpassing strong general-purpose models such as GPT-5.2 and Gemini-3.1-Pro, while also reducing inference latency. Across multiple widely used memory systems, MemPrivacy limits utility loss to within 1.6%, outperforming baseline masking strategies. Overall, MemPrivacy offers an effective balance between privacy protection and personalized memory utility for edge-cloud agents, enabling secure, practical, and user-transparent deployment.