Fairwashing: the risk of rationalization

Abstract

Black-box explanation is the problem of explaining how a machine learning model -- whose internal logic is hidden to the auditor and generally complex -- produces its outcomes. Current approaches for solving this problem include model explanation, outcome explanation as well as model inspection. While these techniques can be beneficial by providing interpretability, they can be used in a negative manner to perform fairwashing, which we define as promoting the false perception that a machine learning model respects some ethical values. In particular, we demonstrate that it is possible to systematically rationalize decisions taken by an unfair black-box model using the model explanation as well as the outcome explanation approaches with a given fairness metric. Our solution, LaundryML, is based on a regularized rule list enumeration algorithm whose objective is to search for fair rule lists approximating an unfair black-box model. We empirically evaluate our rationalization technique on black-box models trained on real-world datasets and show that one can obtain rule lists with high fidelity to the black-box model while being considerably less unfair at the same time.

arXiv commentAccepted to ICML 2019

References in corpus (6)

• Towards A Rigorous Science of Interpretable Machine Learning
• Methods for Interpreting and Understanding Deep Neural Networks
• European Union regulations on algorithmic decision-making and a "right to explanation"
• Equality of Opportunity in Supervised Learning
• Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model
• Towards Robust Interpretability with Self-Explaining Neural Networks

Cited by in corpus (11)

• A survey of algorithmic recourse: definitions, formulations, solutions, and prospects
• Predictive Multiplicity in Classification
• On the Art and Science of Machine Learning Explanations
• The Bouncer Problem: Challenges to Remote Explainability
• Can Explainable AI Explain Unfairness? A Framework for Evaluating Explainable AI
• Proposed Guidelines for the Responsible Use of Explainable Machine Learning
• A simple defense against adversarial attacks on heatmap explanations
• Understanding Prediction Discrepancies in Machine Learning Classifiers
• Challenging common interpretability assumptions in feature attribution explanations
• Aggregating explanation methods for stable and robust explainability
• Partially Interpretable Estimators (PIE): Black-Box-Refined Interpretable Machine Learning