Episode
MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents
- Podcast
- Daily Paper Cast
- Published
- May 14, 2026
- Duration seconds
- 1467
- Processing state
not_requested- Canonical source
- https://share.transistor.fm/s/7e697f9d
Actions
POST https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/memprivacy-privacy-preserving-personalized-memory-management-for-edge-cloud-agents/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/daily-paper-cast-7079649/memprivacy-privacy-preserving-personalized-memory-management-for-edge-cloud-agents.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
🤗 Upvotes: 128 | cs.CR, cs.CL Authors: Yining Chen, Jihao Zhao, Bo Tang, Haofen Wang, Yue Zhang, Fei Huang, Feiyu Xiong, Zhiyu Li Title: MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents Arxiv: http://arxiv.org/abs/2605.09530v2 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 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 prot…