Fairness Shields: Safeguarding against Biased Decision Makers
This addresses fairness issues in AI decision-making for affected individuals, but it is incremental as it builds on existing bias prevention measures.
The paper tackles the problem of AI decision-makers being biased on specific instances despite long-term fairness guarantees, by introducing fairness shields that monitor and intervene to meet fairness criteria while minimizing costs. The result includes four algorithms with empirical evaluation showing effectiveness in ensuring fairness and cost efficiency.
As AI-based decision-makers increasingly influence human lives, it is a growing concern that their decisions are often unfair or biased with respect to people's sensitive attributes, such as gender and race. Most existing bias prevention measures provide probabilistic fairness guarantees in the long run, and it is possible that the decisions are biased on specific instances of short decision sequences. We introduce fairness shielding, where a symbolic decision-maker -- the fairness shield -- continuously monitors the sequence of decisions of another deployed black-box decision-maker, and makes interventions so that a given fairness criterion is met while the total intervention costs are minimized. We present four different algorithms for computing fairness shields, among which one guarantees fairness over fixed horizons, and three guarantee fairness periodically after fixed intervals. Given a distribution over future decisions and their intervention costs, our algorithms solve different instances of bounded-horizon optimal control problems with different levels of computational costs and optimality guarantees. Our empirical evaluation demonstrates the effectiveness of these shields in ensuring fairness while maintaining cost efficiency across various scenarios.