Attack-Resistant Uniform Fairness for Linear and Smooth Contextual Bandits

TL;DR

This paper introduces attack-resistant algorithms for fair contextual bandits, balancing near-optimal regret with fairness guarantees, and addressing vulnerabilities to strategic manipulation.

Contribution

It proposes novel algorithms achieving minimax-optimal regret under fairness constraints and develops robustness against strategic attacks in contextual bandit settings.

Findings

Algorithms maintain fairness and efficiency under attack.

Robust variants achieve optimal regret with attack budgets.

Fairness can be exploited by adversaries with minimal resources.

Abstract

Modern systems, such as digital platforms and service systems, increasingly rely on contextual bandits for online decision-making; however, their deployment can inadvertently create unfair exposure among arms, undermining long-term platform sustainability and supplier trust. This paper studies the contextual bandit problem under a uniform $(1-\delta)$-fairness constraint, and addresses its unique vulnerabilities to strategic manipulation. The fairness constraint ensures that preferential treatment is strictly justified by an arm's actual reward across all contexts and time horizons, using uniformity to prevent statistical loopholes. We develop novel algorithms that achieve (nearly) minimax-optimal regret for both linear and smooth reward functions, while maintaining strong $(1-\tilde{O}(1/T))$-fairness guarantees, and further characterize the theoretically inherent yet asymptotically marginal "price of fairness". However, we reveal that such merit-based fairness becomes uniquely susceptible to signal manipulation. We show that an adversary with a minimal $\tilde{O}(1)$ budget can not only degrade overall performance as in traditional attacks, but also selectively induce insidious fairness-specific failures while leaving conspicuous regret measures largely unaffected. To counter this, we design robust variants incorporating corruption-adaptive exploration and error-compensated thresholding. Our approach yields the first minimax-optimal regret bounds under $C$-budgeted attack while preserving $(1-\tilde{O}(1/T))$-fairness. Numerical experiments and a real-world case demonstrate that our algorithms sustain both fairness and efficiency.