6 papers
Anchored or Drifting: What Recursive Self-Generation Reveals About Training Data
Wojciech Łapacz, Stanisław Pawlak
Large generative models are known to memorize their training data, posing severe privacy risks. Yet, current methods to detect training membership typically rely on the weak signal…
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…
On the Occurence of Critical Learning Periods in Neural Networks
Stanisław Pawlak
This study delves into the plasticity of neural networks, offering empirical support for the notion that critical learning periods and warm-starting performance loss can be avoided…
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…
Addressing The Devastating Effects Of Single-Task Data Poisoning In Exemplar-Free Continual Learning
Stanisław Pawlak, Bartłomiej Twardowski, Tomasz Trzciński +1
Our research addresses the overlooked security concerns related to data poisoning in continual learning (CL). Data poisoning - the intentional manipulation of training data to affe…
Bucks for Buckets (B4B): Active Defenses Against Stealing Encoders
Jan Dubiński, Stanisław Pawlak, Franziska Boenisch +2
Machine Learning as a Service (MLaaS) APIs provide ready-to-use and high-utility encoders that generate vector representations for given inputs. Since these encoders are very costl…