6 papers
BARRIER: Bounded Activation Regions for Robust Information Erasure
Jan Miksa, Patryk Krukowski, Przemysław Spurek +2
Machine unlearning has reached a critical bottleneck. As traditional weight-space interventions focus primarily on erasing targeted concepts, they often fail to prevent the uninten…
Stop Marginalizing My Dreams: Model Inversion via Laplace Kernel for Continual Learning
Patryk Krukowski, Jacek Tabor, Przemysław Spurek +2
Data-free continual learning (DFCIL) relies on model inversion to synthesize pseudo-samples and mitigate catastrophic forgetting. However, existing inversion methods are fundamenta…
InTAct: Interval-based Task Activation Consolidation for Continual Learning
Patryk Krukowski, Jan Miksa, Piotr Helm +3
Continual learning is a fundamental challenge in artificial intelligence that requires networks to acquire new knowledge while preserving previously learned representations. Despit…
SHIELD: Secure Hypernetworks for Incremental Expansion Learning Defense
Patryk Krukowski, Łukasz Gorczyca, Piotr Helm +2
Continual learning under adversarial conditions remains an open problem, as existing methods often compromise either robustness, scalability, or both. We propose a novel framework…
Make Interval Bound Propagation great again
Patryk Krukowski, Daniel Wilczak, Jacek Tabor +2
In various scenarios motivated by real life, such as medical data analysis, autonomous driving, and adversarial training, we are interested in robust deep networks. A network is ro…
HINT: Hypernetwork Approach to Training Weight Interval Regions in Continual Learning
Patryk Krukowski, Anna Bielawska, Kamil Książek +3
Recently, a new Continual Learning (CL) paradigm was presented to control catastrophic forgetting, called Interval Continual Learning (InterContiNet), which relies on enforcing int…