Preprint · 2026 · Open access

Can Agents Keep Secrets They Were Never Told? Benchmarking Latent Privacy Risks Across Sessions with MemJoin

Qishun Yang, Shu Yang, Difei Xu, Di Wang, Meng Ding

arXiv (Cornell University) · Published 17 October 2026 · DOI 10.48550/arxiv.2610.24359

Open PDFView at the publisherCite this paper

In brief

“Can Agents Keep Secrets They Were Never Told? Benchmarking Latent Privacy Risks Across Sessions with MemJoin” is a 2026 preprint by Qishun Yang and 4 co-authors, published in arXiv (Cornell University). OpenAlex counts 0 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
0
References
31
Authors
5

Abstract

To support sustained interactions and personalized assistance, agents use long-term memory to retain and combine user information across sessions. Reusing such memories can lead an agent to state a sensitive relation while completing an ordinary task that does not require it. The relation to protect and the combination of clues that reveal it may remain hidden at memory write time, when later records and tasks are still unknown. In this paper, we introduce MemJoin, a privacy benchmark of 288 synthetic analysis cases in which the complete history entails a sensitive relation, but every individual session is insufficient. We evaluate six memory systems with the same answer-generating model, alongside full-history and no-history controls. Each system writes and updates memories in session order and later retrieves context for an ordinary task, while target annotations remain with the evaluator. We separately check which target attribute values appear in stored records and retrieved context, and whether the final answer states the complete, person-linked relation. In a separate paired test on a prespecified subset, removing shared identifiers and other connecting clues can change complete-relation output while all checked target attribute values remain visible. These findings show why checking attribute visibility alone is insufficient to evaluate what records from different sessions reveal together.

Cite this paper

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

APA 7

Yang, Q., Yang, S., Xu, D., Wang, D., & Ding, M. (2026). Can Agents Keep Secrets They Were Never Told? Benchmarking Latent Privacy Risks Across Sessions with MemJoin. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.24359

MLA 9

Yang, Qishun, et al. “Can Agents Keep Secrets They Were Never Told? Benchmarking Latent Privacy Risks Across Sessions with MemJoin.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2610.24359.

Chicago

Yang, Qishun, Shu Yang, Difei Xu, Di Wang, and Meng Ding. 2026. “Can Agents Keep Secrets They Were Never Told? Benchmarking Latent Privacy Risks Across Sessions with MemJoin.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.24359.

Harvard

Yang, Q. et al. (2026) ‘Can Agents Keep Secrets They Were Never Told? Benchmarking Latent Privacy Risks Across Sessions with MemJoin’, arXiv (Cornell University). doi:10.48550/arxiv.2610.24359.

IEEE

Q. Yang, S. Yang, D. Xu, D. Wang, and M. Ding, “Can Agents Keep Secrets They Were Never Told? Benchmarking Latent Privacy Risks Across Sessions with MemJoin,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2610.24359.

BibTeX

@misc{yang2026agents,
  title     = {{Can Agents Keep Secrets They Were Never Told? Benchmarking Latent Privacy Risks Across Sessions with MemJoin}},
  author    = {Yang, Qishun and Yang, Shu and Xu, Difei and Wang, Di and Ding, Meng},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2610.24359},
  url       = {https://doi.org/10.48550/arxiv.2610.24359}
}

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 risks

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?

Yang, Q., Yang, S., Xu, D., Wang, D., & Ding, M. (2026). Can Agents Keep Secrets They Were Never Told? Benchmarking Latent Privacy Risks Across Sessions with MemJoin. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.24359

How many times has this paper been cited?

0 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?

Qishun Yang, Shu Yang, Difei Xu, Di Wang, Meng Ding.

What is the DOI of this paper?

10.48550/arxiv.2610.24359, permanently at https://doi.org/10.48550/arxiv.2610.24359. 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.