"Is your explanation stable?"
Yuyou Gan, Yuhao Mao, Xuhong Zhang, Shouling Ji, Yuwen Pu, Meng Han, Jianwei Yin, Ting Wang
Abstract
Neural networks have become increasingly popular. Nevertheless, understanding their decision process turns out to be complicated. One vital method to explain a models' behavior is feature attribution, i.e., attributing its decision to pivotal features. Although many algorithms are proposed, most of them aim to improve the faithfulness (fidelity) to the model. However, the real environment contains many random noises, which may cause the feature attribution maps to be greatly perturbed for similar images. More seriously, recent works show that explanation algorithms are vulnerable to adversarial attacks, generating the same explanation for a maliciously perturbed input. All of these make the explanation hard to trust in real scenarios, especially in security-critical applications.