6 papers
SHIELD: Secure Hypernetworks for Incremental Expansion Learning Defense
Patryk Krukowski, Åukasz 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…
BARRIER: Bounded Activation Regions for Robust Information Erasure
Jan Miksa, Patryk Krukowski, PrzemysÅaw 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, PrzemysÅaw 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…
HINT: Hypernetwork Approach to Training Weight Interval Regions in Continual Learning
Patryk Krukowski, Anna Bielawska, Kamil KsiÄ Å¼ek +3
Recently, a new Continual Learning (CL) paradigm was presented to control catastrophic forgetting, called Interval Continual Learning (InterContiNet), which relies on enforcing int…
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…