Causal Fair Metric: Bridging Causality, Individual Fairness, and Adversarial Robustness

Despite the essential need for comprehensive considerations in responsible AI, factors like robustness, fairness, and causality are often studied in isolation. Adversarial perturbation, used to identify vulnerabilities in models, and individual fairness, aiming for equitable treatment of similar individuals, despite initial differences, both depend on metrics to generate comparable input data instances. Previous attempts to define such joint metrics often lack general assumptions about data or structural causal models and were unable to reflect counterfactual proximity. To address this, our …

adversarial causality cs.cy cs.lg differences fair fairness generate identify metrics responsible ai robustness treatment vulnerabilities