Antoni Kowalczuk — accepted AI-conference papers

2026

Finding DoRI: Discovery of Retained Images in Diffusion Models

Antoni Kowalczuk, Dominik Hintersdorf, Lukas Struppek, Kristian Kersting, Adam Dziedzic, Franziska Boenisch

ICML 2026poster

Text-to-image diffusion models (DMs) have achieved remarkable success in image generation. However, concerns about data privacy and intellectual property remain due to their potential to inadvertently memorize and replicate training data. Recent mitigation efforts have focused on identifying and pru…

Cited by 0 Source ↗Scholar ↗

2025

CDI: Copyrighted Data Identification in Diffusion Models

Jan Dubiński, Antoni Kowalczuk, Franziska Boenisch, Adam Dziedzic

CVPR 2025poster

Diffusion Models (DMs) benefit from large and diverse datasets for their training. Since this data is often scraped from the Internet without permission from the data owners, this raises concerns about copyright and intellectual property protections. While (illicit) use of data is easily detected fo…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2025

Privacy Attacks on Image AutoRegressive Models

Antoni Kowalczuk, Jan Dubiński, Franziska Boenisch, Adam Dziedzic

ICML 2025poster

Image AutoRegressive generation has emerged as a new powerful paradigm with image autoregressive models (IARs) matching state-of-the-art diffusion models (DMs) in image quality (FID: 1.48 vs. 1.58) while allowing for a higher generation speed. However, the privacy risks associated with IARs remain u…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗