collaborators

33 papers

cs.LG2026

TabPATE: Differentially Private Tabular In-Context Learning Without Public Data

Dariush Wahdany, Matthew Jagielski, Jesse C. Cresswell +2

Tabular foundation models enable accurate in-context learning (ICL) from small labeled datasets, but the private records placed in context can leak through model predictions. We fi…

cs.LG2026

Dataset Usage Inference without Shadow Models or Held-out Data

Wojciech Łapacz, Stanisław Pawlak, Jan Dubiński +2

How much of my data was used to train a machine learning model? Dataset Usage Inference (DUI) aims to answer this by estimating what fraction of a dataset contributed to a model's…

cs.CV2026

Concept Removal for Frontier Image Generative Models

Aditya Kumar, Pierre Joly, Adam Dziedzic +1

Image generative models are trained on massive, largely uncurated internet-scale datasets that contain undesirable visual concepts. Efficiently removing such concepts from the mode…

cs.LG2026

Natural Identifiers for Privacy and Data Audits in Large Language Models

Lorenzo Rossi, Bartłomiej Marek, Franziska Boenisch +1

Assessing the privacy of large language models (LLMs) presents significant challenges. In particular, most existing methods for auditing differential privacy require the insertion…

cs.CV2026

MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning

Wenhao Wang, Franziska Boenisch, Michael Backes +1

Memorization in machine learning models enables high performance on rare in-distribution samples by capturing their atypical patterns. However, it also causes harmful retention of…

cs.CV2026

Data Provenance for Image Auto-Regressive Generation

Bihe Zhao, Louis Kerner, Michel Meintz +3

Image autoregressive models (IARs) have recently demonstrated remarkable capabilities in visual content generation, achieving photorealistic quality and rapid synthesis through the…