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

TL;DR

MemPrivacy introduces a privacy-preserving memory management approach for edge-cloud agents that identifies sensitive data, replaces it with structured placeholders, and restores it locally, balancing privacy and personalization.

Contribution

It proposes a novel method for privacy protection that maintains memory utility by decoupling privacy masking from semantic destruction, along with a comprehensive evaluation dataset.

Findings

MemPrivacy outperforms GPT-5.2 and Gemini-3.1-Pro in privacy information extraction.

Limits utility loss to within 1.6% across multiple memory systems.

Reduces inference latency while maintaining privacy and personalization.

Abstract

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.