2025

Privacy Attacks On Image AutoRegressive Models

Authors: Antoni Kowalczuk*, Jan Dubiński*, Franziska Boenisch, Adam Dziedzic

Code: GitHub Repository

Blogpost: https://antonikowalczuk.com/blog/priv_iar/, https://sprintml.com/2025/02/04/iars-privacy.html

2024

CDI: Copyrighted Data Identification in Diffusion Models

Authors: Jan Dubiński*, Antoni Kowalczuk*, Franziska Boenisch, Adam Dziedzic

Code: GitHub Repository

Venue: CVPR, 2025, Poster

Rejected from: NeurIPS 2024, AAAI 2025

Benchmarking Robust Self-Supervised Learning Across Diverse Downstream Tasks

Authors: Antoni Kowalczuk*, Jan Dubiński*, Atiyeh Ashari Ghomi*, Yi Sui, George Stein, Jiapeng Wu, Jesse C. Cresswell, Franziska Boenisch, Adam Dziedzic

Venue: ICML Workshop on Foundation Models in the Wild, 2024, Poster

Code: GitHub Repository

Rejected from: ICML 2024 Workshop NextGenAISafety

2023

Towards More Realistic Membership Inference Attacks on Large Diffusion Models

Authors: Jan Dubiński*, Antoni Kowalczuk*, Stanisław Pawlak, Przemysław Rokita, Tomasz Trzciński, Paweł Morawiecki

Venues:

• CVPR EC3V Workshop, 2023, Poster
• MLinPL Conference, 2023, Best Poster Award
• WACV, 2024, Poster

Rejected from: NeurIPS 2023