Conference paper · 2026 · Open access

Out of Tune: How Different Fine-Tuning Methods Affect Information Security

Joseph moretto, Hunter D. Moore

Workshop on Privacy in the Electronic Society, 51–63 · Published 13 October 2026 · DOI 10.1145/3847192.3847356

Open full textCite this paper

In brief

“Out of Tune: How Different Fine-Tuning Methods Affect Information Security” is a 2026 conference paper by Joseph moretto and Hunter D. Moore, published in Workshop on Privacy in the Electronic Society. 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 Workshop on Privacy in the Electronic Society.

Citations
0
References
28
Authors
2

Abstract

Fine-tuning large language models (LLMs) enables task specialization but introduces privacy risks through training data memorization. Practitioners deploying fine-tuned LLMs in sensitive domains such as medicine, law, and finance must choose among fine-tuning methods without clear guidance on the privacy implications of that choice. We compare full fine-tuning, partial fine-tuning, and Low-Rank Adaptation (LoRA) by measuring how much sensitive personally identifiable information (PII) each method leaks from training data, using planted canaries to track memorization. Six Llama configurations (3B and 8B parameters) are evaluated across the medical, legal, and finance domains under three extraction attack types: prefix attacks, random prompting, and completion attacks. Full fine-tuning leaks the most on average, followed by LoRA. Partial fine-tuning leaks the least in every configuration we tested, though the relative ordering of full fine-tuning and LoRA varies. Contrary to our initial hypothesis, LoRA's parameter efficiency does not yield the strongest privacy protection; we attribute this to LoRA's architectural breadth across all transformer layers. The performance-privacy trade-off these findings expose has direct consequences for deployment. Even partial fine-tuning on the 3B model, our best configuration, leaked canaries, so practitioners should assume some leakage by default.

Cite this paper

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

APA 7

moretto, J., & Moore, H. D. (2026). Out of Tune: How Different Fine-Tuning Methods Affect Information Security. Workshop on Privacy in the Electronic Society, 51–63. https://doi.org/10.1145/3847192.3847356

MLA 9

moretto, Joseph, and Hunter D. Moore. “Out of Tune: How Different Fine-Tuning Methods Affect Information Security.” Workshop on Privacy in the Electronic Society, 2026, pp. 51–63. https://doi.org/10.1145/3847192.3847356.

Chicago

moretto, Joseph and Hunter D. Moore. 2026. “Out of Tune: How Different Fine-Tuning Methods Affect Information Security.” Workshop on Privacy in the Electronic Society: 51–63. https://doi.org/10.1145/3847192.3847356.

Harvard

moretto, J. and Moore, H. D. (2026) ‘Out of Tune: How Different Fine-Tuning Methods Affect Information Security’, Workshop on Privacy in the Electronic Society, pp. 51–63. doi:10.1145/3847192.3847356.

IEEE

J. moretto and H. D. Moore, “Out of Tune: How Different Fine-Tuning Methods Affect Information Security,” Workshop on Privacy in the Electronic Society, pp. 51–63, 2026, doi: 10.1145/3847192.3847356.

BibTeX

@inproceedings{moretto2026tune,
  title     = {{Out of Tune: How Different Fine-Tuning Methods Affect Information Security}},
  author    = {moretto, Joseph and Moore, Hunter D.},
  booktitle = {Workshop on Privacy in the Electronic Society},
  year      = {2026},
  pages     = {51--63},
  doi       = {10.1145/3847192.3847356},
  url       = {https://doi.org/10.1145/3847192.3847356}
}

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
  • fine-tuning
  • training data memorization
  • privacy leakage
  • personally identifiable information
  • low-rank adaptation
  • partial fine-tuning
  • full fine-tuning

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?

moretto, J., & Moore, H. D. (2026). Out of Tune: How Different Fine-Tuning Methods Affect Information Security. Workshop on Privacy in the Electronic Society, 51–63. https://doi.org/10.1145/3847192.3847356

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 Workshop on Privacy in the Electronic Society: sign in and open the full text from this page.

Who wrote this paper?

Joseph moretto, Hunter D. Moore.

What is the DOI of this paper?

10.1145/3847192.3847356, permanently at https://doi.org/10.1145/3847192.3847356. 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.