← Search

Amir Mehrpanah

2 accepted papers

2026

Improving Adversarial Robustness of Attribution via Implicit Regularization

ICML 2026poster

The adversarial robustness of attributions is a fundamental requirement for reliable explainability in deep learning, yet existing approaches typically rely on computationally expensive explicit regularization. In this work, we show that attribution robustness can arise implicitly from the learning …

Cited by 0SourceScholar
2025

On the Complexity-Faithfulness Trade-off of Gradient-Based Explanations

ICCV 2025poster

ReLU networks, while prevalent for visual data, have sharp transitions, sometimes relying on individual pixels for predictions, making vanilla gradient-based explanations noisy and difficult to interpret. Existing methods, such as GradCAM, smooth these explanations by producing surrogate models at t…