Preprint · 2026 · Open access

Stop Tracking Me! Proactive Defense Against Attribute Inference Attack in LLMs

Dong Yan, Jian Liang, Ran He, T.N. Tan

arXiv (Cornell University) · Published 12 February 2026 · DOI 10.48550/arxiv.2602.11528

Open PDFView at the publisherCite this paper

In brief

“Stop Tracking Me! Proactive Defense Against Attribute Inference Attack in LLMs” is a 2026 preprint by Dong Yan and 3 co-authors, published in arXiv (Cornell University). OpenAlex counts 1 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
1
Most cited in
2026 (1)
References
34
Authors
4

Abstract

Recent studies have shown that large language models (LLMs) can infer private user attributes (e.g., age, location, gender) from user-generated text shared online, enabling rapid and large-scale privacy breaches. Existing anonymization-based defenses are coarse-grained, lacking word-level precision in anonymizing privacy-leaking elements. Moreover, they are inherently limited as altering user text to hide sensitive cues still allows attribute inference to occur through models' reasoning capabilities. To address these limitations, we propose a unified defense framework that combines fine-grained anonymization (TRACE) with inference-preventing optimization (RPS). TRACE leverages attention mechanisms and inference chain generation to identify and anonymize privacy-leaking textual elements, while RPS employs a lightweight two-stage optimization strategy to induce model rejection behaviors, thereby preventing attribute inference. Evaluations across diverse LLMs show that TRACE-RPS reduces attribute inference accuracy from around 50\% to below 5\% on open-source models. In addition, our approach offers strong cross-model generalization, prompt-variation robustness, and utility-privacy tradeoffs. Our code is available at https://github.com/Jasper-Yan/TRACE-RPS.

Cite this paper

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

APA 7

Yan, D., Liang, J., He, R., & Tan, T. (2026). Stop Tracking Me! Proactive Defense Against Attribute Inference Attack in LLMs. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2602.11528

MLA 9

Yan, Dong, et al. “Stop Tracking Me! Proactive Defense Against Attribute Inference Attack in LLMs.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2602.11528.

Chicago

Yan, Dong, Jian Liang, Ran He, and T.N. Tan. 2026. “Stop Tracking Me! Proactive Defense Against Attribute Inference Attack in LLMs.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2602.11528.

Harvard

Yan, D. et al. (2026) ‘Stop Tracking Me! Proactive Defense Against Attribute Inference Attack in LLMs’, arXiv (Cornell University). doi:10.48550/arxiv.2602.11528.

IEEE

D. Yan, J. Liang, R. He, and T. Tan, “Stop Tracking Me! Proactive Defense Against Attribute Inference Attack in LLMs,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2602.11528.

BibTeX

@misc{yan2026stop,
  title     = {{Stop Tracking Me! Proactive Defense Against Attribute Inference Attack in LLMs}},
  author    = {Yan, Dong and Liang, Jian and He, Ran and Tan, T.N.},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2602.11528},
  url       = {https://doi.org/10.48550/arxiv.2602.11528}
}

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

  • attribute inference attacks
  • large language models
  • privacy preservation
  • user-generated text
  • age estimation
  • location inference
  • gender inference
  • privacy-utility trade-off

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?

Yan, D., Liang, J., He, R., & Tan, T. (2026). Stop Tracking Me! Proactive Defense Against Attribute Inference Attack in LLMs. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2602.11528

How many times has this paper been cited?

1 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?

Dong Yan, Jian Liang, Ran He, T.N. Tan.

What is the DOI of this paper?

10.48550/arxiv.2602.11528, permanently at https://doi.org/10.48550/arxiv.2602.11528. 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.