activity
20242026
collaborators

7 papers

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

Privacy Attacks on Image AutoRegressive Models

Antoni Kowalczuk, Jan Dubiński, Franziska Boenisch +1

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 (FI…

cs.LG2026

Universal Properties of Activation Sparsity in Modern Large Language Models

Filip Szatkowski, Patryk Będkowski, Alessio Devoto +5

Activation sparsity is an intriguing property of deep neural networks that has been extensively studied in ReLU-based models, due to its advantages for efficiency, robustness, and…

cs.LG2025

On Stealing Graph Neural Network Models

Marcin Podhajski, Jan Dubiński, Franziska Boenisch +3

Current graph neural network (GNN) model-stealing methods rely heavily on queries to the victim model, assuming no hard query limits. However, in reality, the number of allowed que…

cs.LG2025

Backdoor Vectors: a Task Arithmetic View on Backdoor Attacks and Defenses

Stanisław Pawlak, Jan Dubiński, Daniel Marczak +1

Model merging (MM) recently emerged as an effective method for combining large deep learning models. However, it poses significant security risks. Recent research shows that it is…

cs.LG2024

Efficient Model-Stealing Attacks Against Inductive Graph Neural Networks

Marcin Podhajski, Jan Dubiński, Franziska Boenisch +3

Graph Neural Networks (GNNs) are recognized as potent tools for processing real-world data organized in graph structures. Especially inductive GNNs, which allow for the processing…