5 papers
Amplifying Membership Signal Through Chained Regeneration
Wojciech Åapacz, StanisÅaw Pawlak
The tendency of large generative models to memorize training data makes sample verification critical for privacy auditing and copyright enforcement. Current membership (MIA) and da…
Dataset Usage Inference without Shadow Models or Held-out Data
Wojciech Åapacz, StanisÅaw Pawlak, Jan DubiÅski +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
StanisÅaw 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
StanisÅaw Pawlak, Jan DubiÅski, 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
StanisÅaw Pawlak, BartÅomiej Twardowski, Tomasz TrzciÅski +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…