Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods
Dylan Slack*, Sophie Hilgard*, Emiliy Jia, Sameer Singh, and Himabindu Lakkaraju
AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society (AIES), 2020
Also accepted at SafeAI Workshop, AAAI, 2020
As machine learning black boxes are increasingly being deployed in domains such as healthcare and criminal justice, there is growing emphasis on building tools and techniques for explaining these black boxes in an interpretable manner. Such explanations are being leveraged by domain experts to diagnose systematic errors and underlying biases of black boxes. In this paper, we demonstrate that post hoc explanations techniques that rely on input perturbations, such as LIME and SHAP, are not reliable. Specifically, we propose a novel scaffolding technique that effectively hides the biases of a given classifier by allowing an adversarial entity to craft an arbitrary desired explanation. Our approach can be used to scaffold any biased classifier in such a way that its predictions on the input data distribution still remain biased, but the posthoc explanations of the scaffolded classifier look innocuous. Using extensive evaluation with multiple real world datasets (including COMPAS), we demonstrate how extremely biased (racist) classifiers crafted by our framework can easily fool popular explanation techniques such as LIME and SHAP into generating innocuous explanations which do not reflect the underlying biases.
Paper / Code / Poster / Bibtex
Note: This work was previously called How can we fool LIME and SHAP? Adversarial Attacks on Post hoc Explanation Methods.