Auditing fairness under unawareness through counterfactual reasoning |
| |
| Institution: | 1. Department of Management, Beijing Electronic Science & Technology Institute, Beijing, 100070, China;2. Department of Cybersecurity, Beijing Electronic Science & Technology Institute, Beijing, 100070, China;1. USC-SJTU Institute of Cultural and Creative Industry, Shanghai Jiao Tong University, 800 Dong Chuan Road, Shanghai, China, 200240;2. Sol Price School of Public Policy, University of Southern California, Los Angeles;1. School of Cyber Science and Engineering, Sichuan University, Chengdu, China;2. Cybersecurity Research Institute, Sichuan University, Chengdu, China |
| |
| Abstract: | Artificial intelligence (AI) is rapidly becoming the pivotal solution to support critical judgments in many life-changing decisions. In fact, a biased AI tool can be particularly harmful since these systems can contribute to or demote people’s well-being. Consequently, government regulations are introducing specific rules to prohibit the use of sensitive features (e.g., gender, race, religion) in the algorithm’s decision-making process to avoid unfair outcomes. Unfortunately, such restrictions may not be sufficient to protect people from unfair decisions as algorithms can still behave in a discriminatory manner. Indeed, even when sensitive features are omitted (fairness through unawareness), they could be somehow related to other features, named proxy features. This study shows how to unveil whether a black-box model, complying with the regulations, is still biased or not. We propose an end-to-end bias detection approach exploiting a counterfactual reasoning module and an external classifier for sensitive features. In detail, the counterfactual analysis finds the minimum cost variations that grant a positive outcome, while the classifier detects non-linear patterns of non-sensitive features that proxy sensitive characteristics. The experimental evaluation reveals the proposed method’s efficacy in detecting classifiers that learn from proxy features. We also scrutinize the impact of state-of-the-art debiasing algorithms in alleviating the proxy feature problem. |
| |
| Keywords: | Fairness Discrimination Counterfactual reasoning Proxy features |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
