Improving LIME Robustness with Smarter Locality Sampling

2020/06/22 by Sean Saito, Eugene Chua, Saito, Sean +5 · 2 citations
Computer Science · #Explainable Artificial Intelligence (XAI) #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications

paper · pdf · doi:10.48550/arxiv.2006.12302

Abstract

Explainability algorithms such as LIME have enabled machine learning systems to adopt transparency and fairness, which are important qualities in commercial use cases. However, recent work has shown that LIME's naive sampling strategy can be exploited by an adversary to conceal biased, harmful behavior. We propose to make LIME more robust by training a generative adversarial network to sample more realistic synthetic data which the explainer uses to generate explanations. Our experiments demonstrate that our proposed method demonstrates an increase in accuracy across three real-world datasets in detecting biased, adversarial behavior compared to vanilla LIME. This is achieved while maintaining comparable explanation quality, with up to 99.94% in top-1 accuracy in some cases.

Cited by

• Better sampling in explanation methods can prevent dieselgate-like deception
• On Locality of Local Explanation Models

Related

• Bridging Interpretability and Robustness Using LIME-Guided Model Refinement
• SHLIME: Foiling adversarial attacks fooling SHAP and LIME
• GLIME: General, Stable and Local LIME Explanation
• Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation\n Methods
• Are Your Explanations Reliable? Investigating the Stability of LIME in Explaining Text Classifiers by Marrying XAI and Adversarial Attack