Home | Publications | SRK+26

Unintended Memorization of Sensitive Information in Fine-Tuned Language Models

MCML Authors

Georgios Kaissis

Georgios Kaissis

Dr.

Principal Investigator

* Former Principal Investigator

Abstract

Fine-tuning Large Language Models (LLMs) on sensitive datasets carries a substantial risk of unintended memorization and leakage of Personally Identifiable Information (PII), which can violate privacy regulations and compromise individual safety. In this work, we systematically investigate a critical and underexplored vulnerability: the exposure of PII that appears only in model inputs, not in training targets. Using both synthetic and real-world datasets, we design controlled extraction probes to quantify unintended PII memorization and study how factors such as language, PII frequency, task type, and model size influence memorization behavior. We further benchmark four privacy-preserving approaches including differential privacy, machine unlearning, regularization, and preference alignment, evaluating their trade-offs between privacy and task performance. Our results show that post-training methods generally provide more consistent privacy-utility trade-offs, while differential privacy achieves strong reduction in leakage in specific settings, although it can introduce training instability. These findings highlight the persistent challenge of memorization in fine-tuned LLMs and emphasize the need for robust, scalable privacy-preserving techniques.

inproceedings SRK+26


EACL 2026

19th Conference of the European Chapter of the Association for Computational Linguistics. Rabat, Morocco, Mar 24-29, 2026.
Conference logo
A Conference

Authors

M. Szep • J. M. Ruiz • G. Kaissis • P. Seidl • R. von Eisenhart-Rothe • F. Hinterwimmer • D. Rückert

Links

DOI

Research Area

 C1 | Medicine

BibTeXKey: SRK+26

Back to Top