iiinova — where your digital self keeps evolving

Marton Szep

@martonszep.bsky.social

I am a PhD candidate at TUM. My doctoral research in Medical NLP develops reliable LLM-based methods for clinical decision support and workflow optimization under the constraints of domain specificity and limited, sensitive clinical data.

Posts Replies Media

Reposted by Marton Szep

Differential Privacy Papers @dppapers.bsky.social · 27/01/2026

Unintended Memorization of Sensitive Information in Fine-Tuned Language Models Marton Szep, Jorge Marin Ruiz, Georgios Kaissis, Paulina Seidl, Rüdiger von Eisenhart-Rothe, Florian Hinterwimmer, Daniel Rueckert arxiv.org/abs/2601.17480

011

Marton Szep @martonszep.bsky.social · 10/03/2026

Thrilled to present our paper "Unintended Memorization of Sensitive Information in Fine-Tuned Language Models" at #EACL2026 in Rabat! 🇲🇦 w/ J. Marin Ruiz, G. Kaissis, P. Seidl, R. v. Eisenhart-Rothe, F. Hinterwimmer & @danielrueckert.bsky.social. Read here: arxiv.org/abs/2601.174...

A promotional graphic for an oral presentation at the EACL 2026 conference in Morocco. The background features a sunny, historic Moroccan stone fortress gate with palm trees, a clear blue sky, and decorative geometric tile patterns in the corners. Text in the top left indicates the event is at Palais Des Congres, Rabat, from March 24-29, 2026. A banner across the middle displays the presentation title: "Unintended Memorization of Sensitive Information in Fine-Tuned Language Models." Below the title is a flowchart diagram illustrating how Large Language Models (LLMs) trained on sensitive medical text can inadvertently memorize Personally Identifiable Information (PII), and how a "True-Prefix Attack" can extract a patient's name even when fine-tuned for downstream tasks that do not contain PII. Text at the very bottom reads, "Oral Presentation: March 27 | 11:00 AM | Salle La Palmeraie."

252