Preprint · 2025 · Open access

Position: Privacy Is Not Just Memorization!

Niloofar Mireshghallah, Tianshi Li

arXiv (Cornell University) · Published 2 October 2025 · DOI 10.48550/arxiv.2510.01645

Open PDFView at the publisherCite this paper

In brief

“Position: Privacy Is Not Just Memorization!” is a 2025 preprint by Niloofar Mireshghallah and Tianshi Li, published in arXiv (Cornell University). OpenAlex counts 33 citations as of 19 November 2026. It is open access under a CC BY-SA licence: the full text is free to read at arXiv (Cornell University).

Citations
33
Most cited in
2026 (31)
References
61
Authors
2

Abstract

The discourse on privacy risks in Large Language Models (LLMs) has disproportionately focused on verbatim memorization of training data, while a constellation of more immediate and scalable privacy threats remain underexplored. This position paper argues that the privacy landscape of LLM systems extends far beyond training data extraction, encompassing risks from data collection practices, inference-time context leakage, autonomous agent capabilities, and the democratization of surveillance through deep inference attacks. We present a comprehensive taxonomy of privacy risks across the LLM lifecycle -- from data collection through deployment -- and demonstrate through case studies how current privacy frameworks fail to address these multifaceted threats. Through a longitudinal analysis of 1,322 AI/ML privacy papers published at leading conferences over the past decade (2016--2025), we reveal that while memorization receives outsized attention in technical research, the most pressing privacy harms lie elsewhere, where current technical approaches offer little traction and viable paths forward remain unclear. We call for a fundamental shift in how the research community approaches LLM privacy, moving beyond the narrow focus of current technical solutions and embracing interdisciplinary approaches that address the sociotechnical nature of these emerging threats.

Cite this paper

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

APA 7

Mireshghallah, N., & Li, T. (2025). Position: Privacy Is Not Just Memorization! arXiv (Cornell University). https://doi.org/10.48550/arxiv.2510.01645

MLA 9

Mireshghallah, Niloofar, and Tianshi Li. “Position: Privacy Is Not Just Memorization!” arXiv (Cornell University), 2025. https://doi.org/10.48550/arxiv.2510.01645.

Chicago

Mireshghallah, Niloofar and Tianshi Li. 2025. “Position: Privacy Is Not Just Memorization!” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2510.01645.

Harvard

Mireshghallah, N. and Li, T. (2025) ‘Position: Privacy Is Not Just Memorization!’, arXiv (Cornell University). doi:10.48550/arxiv.2510.01645.

IEEE

N. Mireshghallah and T. Li, “Position: Privacy Is Not Just Memorization!,” arXiv (Cornell University), 2025, doi: 10.48550/arxiv.2510.01645.

BibTeX

@misc{mireshghallah2025position,
  title     = {{Position: Privacy Is Not Just Memorization!}},
  author    = {Mireshghallah, Niloofar and Li, Tianshi},
  howpublished = {arXiv (Cornell University)},
  year      = {2025},
  doi       = {10.48550/arxiv.2510.01645},
  url       = {https://doi.org/10.48550/arxiv.2510.01645}
}

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

  • large language models
  • AI privacy
  • memorization
  • training data leakage
  • autonomous agents
  • surveillance
  • data collection practices
  • privacy framework

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?

Mireshghallah, N., & Li, T. (2025). Position: Privacy Is Not Just Memorization! arXiv (Cornell University). https://doi.org/10.48550/arxiv.2510.01645

How many times has this paper been cited?

33 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?

Niloofar Mireshghallah, Tianshi Li.

What is the DOI of this paper?

10.48550/arxiv.2510.01645, permanently at https://doi.org/10.48550/arxiv.2510.01645. 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.