6 papers
The Reliability Gap in Benchmark Auditing: Distribution Shift and Scale as Failure Modes of Contamination Detection
Wojciech Zarzecki, Jan DubiÅski, Sebastian Cygert
Benchmark contamination, where evaluation examples appear in a model's training data, threatens the validity of LLM assessment. Statistical tools for detecting training-data member…
Efficient LLM Moderation with Multi-Layer Latent Prototypes
Maciej ChrabÄ szcz, Filip Szatkowski, Bartosz Wójcik +3
Although modern LLMs are aligned with human values during post-training, robust moderation remains essential to prevent harmful outputs at deployment time. Existing approaches suff…
Membership and Dataset Inference Attacks on Large Audio Generative Models
Jakub Proboszcz, PaweÅ Kochanski, Karol Korszun +5
Generative audio models, based on diffusion and autoregressive architectures, have advanced rapidly in both quality and expressiveness. This progress, however, raises pressing copy…
ExpertSim: Fast Particle Detector Simulation Using Mixture-of-Generative-Experts
Patryk BÄdkowski, Jan DubiÅski, Filip Szatkowski +3
Simulating detector responses is a crucial part of understanding the inner workings of particle collisions in the Large Hadron Collider at CERN. Such simulations are currently perf…
Radioactive Watermarks in Diffusion and Autoregressive Image Generative Models
Michel Meintz, Jan DubiÅski, Franziska Boenisch +1
Image generative models have become increasingly popular, but training them requires large datasets that are costly to collect and curate. To circumvent these costs, some parties m…
CDI: Copyrighted Data Identification in Diffusion Models
Jan DubiÅski, Antoni Kowalczuk, Franziska Boenisch +1
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…