Skip to content
conftrace_

attribution robustness

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

removal-based attribution (1) explanation attack (1) model perturbation (1) explanation method (1) input perturbation (1) lipschitz regularity (1) adversarial perturbation (1) deep neural network (1) feature attribution (1) text classification (1)

Papers

On the Robustness of Removal-Based Feature Attributions NeurIPS 2023 Fooling Explanations in Text Classifiers ICLR 2022