Login / Signup

Can We Really Trust Explanations? Evaluating the Stability of Feature Attribution Explanation Methods via Adversarial Attack.

Zhao YangYuanzhe ZhangZhongtao JiangYiming JuJun ZhaoKang Liu
Published in: CCL (2022)
Keyphrases
  • preprocessing
  • empirical studies
  • multi agent
  • significant improvement
  • computational cost
  • neural network
  • decision trees
  • classification method
  • statistical methods
  • qualitative and quantitative