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 155k 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.

翻译：随着基于大语言模型的代理在边缘-云端环境中日益普及，个性化记忆已成为实现长期适应用户需求和用户中心交互的关键技术。然而，云端辅助的记忆管理会暴露敏感用户信息，而现有隐私保护方法通常依赖激进式掩蔽，该方式会移除与任务相关的语义信息，从而导致记忆效用和个性化质量下降。为应对此挑战，本文提出MemPrivacy方法，其在边缘设备上识别隐私敏感片段，用语义结构化的类型感知占位符替换这些片段以供云端记忆处理，并在需要时在本地恢复原始值。通过将隐私保护与语义破坏解耦，MemPrivacy在最小化敏感数据暴露的同时，保留了有效记忆形成与检索所需的信息。我们还构建了用于系统评估的MemPrivacy-Bench数据集，覆盖200个用户及超过15.5万个隐私实例，并引入四层级隐私分类体系以支持可配置的保护策略。实验表明，MemPrivacy在隐私信息提取方面表现优异，显著超越GPT-5.2和Gemini-3.1-Pro等强通用模型，同时降低了推理延迟。在多种广泛应用的记忆系统中，MemPrivacy将效用损失控制在1.6%以内，优于基线掩蔽策略。总体而言，MemPrivacy为边缘-云端代理在隐私保护与个性化记忆效用之间提供了有效平衡，支持安全、实用且对用户透明的部署。