Preprint · 2026 · Open access

ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying

Xingyu Lyu, Jianfeng He, Ning Wang, Yidan Hu, Tao Li, Danjue Chen, Shixiong Li, Yimin Chen

arXiv (Cornell University) · Published 10 April 2026 · DOI 10.48550/arxiv.2604.09747

Open PDFView at the publisherCite this paper

In brief

“ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying” is a 2026 preprint by Xingyu Lyu and 7 co-authors, published in arXiv (Cornell University). OpenAlex counts 7 citations as of 19 November 2026. It is open access under a CC BY-NC-SA licence: the full text is free to read at arXiv (Cornell University).

Citations
7
Most cited in
2026 (7)
References
35
Authors
8

Abstract

Large Language Model (LLM) agents have achieved rapid adoption and demonstrated remarkable capabilities across a wide range of applications. To improve reasoning and task execution, modern LLM agents would incorporate memory modules or retrieval-augmented generation (RAG) mechanisms, enabling them to further leverage prior interactions or external knowledge. However, such a design also introduces a group of critical privacy vulnerabilities: sensitive information stored in memory can be leaked through query-based attacks. Although feasible, existing attacks often achieve only limited performance, with low attack success rates (ASR). In this paper, we propose ADAM, a novel privacy attack that features data distribution estimation of a victim agent's memory and employs an entropy-guided query strategy for maximizing privacy leakage. Extensive experiments demonstrate that our attack substantially outperforms state-of-the-art ones, achieving up to 100% ASRs. These results thus underscore the urgent need for robust privacy-preserving methods for current LLM agents.

Cite this paper

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

APA 7

Lyu, X., He, J., Wang, N., Hu, Y., Li, T., Chen, D., Li, S., & Chen, Y. (2026). ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2604.09747

MLA 9

Lyu, Xingyu, et al. “ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2604.09747.

Chicago

Lyu, Xingyu, Jianfeng He, Ning Wang, Yidan Hu, Tao Li, Danjue Chen, Shixiong Li, and Yimin Chen. 2026. “ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2604.09747.

Harvard

Lyu, X. et al. (2026) ‘ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying’, arXiv (Cornell University). doi:10.48550/arxiv.2604.09747.

IEEE

X. Lyu et al., “ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2604.09747.

BibTeX

@misc{lyu2026adam,
  title     = {{ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying}},
  author    = {Lyu, Xingyu and He, Jianfeng and Wang, Ning and Hu, Yidan and Li, Tao and Chen, Danjue and Li, Shixiong and Chen, Yimin},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2604.09747},
  url       = {https://doi.org/10.48550/arxiv.2604.09747}
}

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

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning

  • LLM agents
  • agent memory
  • privacy attacks
  • data extraction attacks
  • retrieval-augmented generation
  • query-based attacks
  • data distribution estimation
  • privacy leakage

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?

Lyu, X., He, J., Wang, N., Hu, Y., Li, T., Chen, D., Li, S., & Chen, Y. (2026). ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2604.09747

How many times has this paper been cited?

7 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?

Xingyu Lyu, Jianfeng He, Ning Wang, Yidan Hu, Tao Li, Danjue Chen, Shixiong Li, Yimin Chen.

What is the DOI of this paper?

10.48550/arxiv.2604.09747, permanently at https://doi.org/10.48550/arxiv.2604.09747. 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.