3 papers
cs.LG2026
Improving Adversarial Robustness of Attribution via Implicit Regularization
Amir Mehrpanah, Matteo Gamba, Hossein Azizpour
The adversarial robustness of attributions is a fundamental requirement for reliable explainability in deep learning, yet existing approaches typically rely on computationally expe…
cs.LG2025
On Spectral Properties of Gradient-based Explanation Methods
Amir Mehrpanah, Erik Englesson, Hossein Azizpour
Understanding the behavior of deep networks is crucial to increase our confidence in their results. Despite an extensive body of work for explaining their predictions, researchers…
cs.LG2025
On the Complexity-Faithfulness Trade-off of Gradient-Based Explanations
Amir Mehrpanah, Matteo Gamba, Kevin Smith +1
ReLU networks, while prevalent for visual data, have sharp transitions, sometimes relying on individual pixels for predictions, making vanilla gradient-based explanations noisy and…