5 citations · 19 across the 15 of their papers we have counts for
3 papers · 1 filter
Adversarial alignment: Breaking the trade-off between the strength of an attack and its relevance to human perception
Drew Linsley, Pinyuan Feng, Thibaut Boissin +4
Deep neural networks (DNNs) are known to have a fundamental sensitivity to adversarial attacks, perturbations of the input that are imperceptible to humans yet powerful enough to c…
Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization
Thomas Fel, Thibaut Boissin, Victor Boutin +9
Feature visualization has gained substantial popularity, particularly after the influential work by Olah et al. in 2017, which established it as a crucial tool for explainability.…
CRAFT: Concept Recursive Activation FacTorization for Explainability
Thomas Fel, Agustin Picard, Louis Bethune +5
Attribution methods, which employ heatmaps to identify the most influential regions of an image that impact model decisions, have gained widespread popularity as a type of explaina…