Preprint · 2026 · Open access

MRMMIA: Membership Inference Attacks on Memory in Chat Agents

Kai Chen, Yan Pang, Tianhao Wang

arXiv (Cornell University) · Published 27 May 2026 · DOI 10.48550/arxiv.2605.27825

Open PDFView at the publisherCite this paper

In brief

“MRMMIA: Membership Inference Attacks on Memory in Chat Agents” is a 2026 preprint by Kai Chen and 2 co-authors, published in arXiv (Cornell University). OpenAlex counts 4 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
4
Most cited in
2026 (4)
References
29
Authors
3

Abstract

Membership inference attacks (MIAs) test whether a target data record belongs to a system's private data, and have become a standard tool to measure privacy leakage in machine learning systems. Prior work has primarily focused on training corpora or retrieval databases. However, MIAs against agent memory have received less attention, even though such memory can contain sensitive user-agent interactions, retrieved facts, and user preferences. Therefore, in this work, we focus on chat agent memory MIAs, where an adversary infers whether a candidate memory unit belongs to the chat agent's memory store. We propose Multi-Recall Memory MIA (MRMMIA), a unified attack that utilizes multiple recall probes to the agent to extract the membership signal across black-box, gray-box, and white-box settings. Our experiments demonstrate that MRMMIA consistently outperforms baselines. Our results expose the privacy risk in agents and provide an initial evaluation framework for membership leakage in chat-agent memory systems.

Cite this paper

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

APA 7

Chen, K., Pang, Y., & Wang, T. (2026). MRMMIA: Membership Inference Attacks on Memory in Chat Agents. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2605.27825

MLA 9

Chen, Kai, et al. “MRMMIA: Membership Inference Attacks on Memory in Chat Agents.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2605.27825.

Chicago

Chen, Kai, Yan Pang, and Tianhao Wang. 2026. “MRMMIA: Membership Inference Attacks on Memory in Chat Agents.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2605.27825.

Harvard

Chen, K., Pang, Y. and Wang, T. (2026) ‘MRMMIA: Membership Inference Attacks on Memory in Chat Agents’, arXiv (Cornell University). doi:10.48550/arxiv.2605.27825.

IEEE

K. Chen, Y. Pang, and T. Wang, “MRMMIA: Membership Inference Attacks on Memory in Chat Agents,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2605.27825.

BibTeX

@misc{chen2026mrmmia,
  title     = {{MRMMIA: Membership Inference Attacks on Memory in Chat Agents}},
  author    = {Chen, Kai and Pang, Yan and Wang, Tianhao},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2605.27825},
  url       = {https://doi.org/10.48550/arxiv.2605.27825}
}

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

  • membership inference attacks
  • agent memory
  • privacy leakage
  • black-box attacks
  • gray-box attacks
  • white-box attacks
  • user-agent interaction

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, K., Pang, Y., & Wang, T. (2026). MRMMIA: Membership Inference Attacks on Memory in Chat Agents. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2605.27825

How many times has this paper been cited?

4 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?

Kai Chen, Yan Pang, Tianhao Wang.

What is the DOI of this paper?

10.48550/arxiv.2605.27825, permanently at https://doi.org/10.48550/arxiv.2605.27825. 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.