Preprint · 2026 · Open access

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

Yining Chen, Jihao Zhao, Bo Tang, Haofen Wang, Yue Zhang, Fei Huang, Feiyu Xiong, Zhiyu Li

arXiv (Cornell University) · Published 10 May 2026 · DOI 10.48550/arxiv.2605.09530

Open PDFView at the publisherCite this paper

In brief

“MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents” is a 2026 preprint by Yining Chen and 7 co-authors, published in arXiv (Cornell University). OpenAlex counts 13 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
13
Most cited in
2026 (13)
References
54
Authors
8

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.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Chen, Y., Zhao, J., Tang, B., Wang, H., Zhang, Y., Huang, F., Xiong, F., & Li, Z. (2026). MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2605.09530

MLA 9

Chen, Yining, et al. “MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2605.09530.

Chicago

Chen, Yining, Jihao Zhao, Bo Tang, Haofen Wang, Yue Zhang, Fei Huang, Feiyu Xiong, and Zhiyu Li. 2026. “MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2605.09530.

Harvard

Chen, Y. et al. (2026) ‘MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents’, arXiv (Cornell University). doi:10.48550/arxiv.2605.09530.

IEEE

Y. Chen et al., “MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2605.09530.

BibTeX

@misc{chen2026memprivacy,
  title     = {{MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents}},
  author    = {Chen, Yining and Zhao, Jihao and Tang, Bo and Wang, Haofen and Zhang, Yue and Huang, Fei and Xiong, Feiyu and Li, Zhiyu},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2605.09530},
  url       = {https://doi.org/10.48550/arxiv.2605.09530}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data

  • privacy preservation
  • LLM agents
  • sensitive data exposure
  • privacy taxonomy
  • inference latency reduction

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Chen, Y., Zhao, J., Tang, B., Wang, H., Zhang, Y., Huang, F., Xiong, F., & Li, Z. (2026). MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2605.09530

How many times has this paper been cited?

13 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Yining Chen, Jihao Zhao, Bo Tang, Haofen Wang, Yue Zhang, Fei Huang, Feiyu Xiong, Zhiyu Li.

What is the DOI of this paper?

10.48550/arxiv.2605.09530, permanently at https://doi.org/10.48550/arxiv.2605.09530. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.