Strategic Oversight for AI Safety: A Stackelberg Security Games Perspective

Abstract

Existing safety frameworks of artificial intelligence (AI) systems largely treat alignment as a static optimization problem (e.g., tuning models to desired behavior) while overlooking the dynamic, adversarial incentives that shape how data are collected, how models are evaluated, and how they are ultimately deployed. We propose a new perspective on AI safety grounded in Stackelberg Security Games (SSGs): a class of game-theoretic models designed for adversarial resource allocation under uncertainty. By viewing AI oversight as a strategic interaction between defenders (auditors, evaluators, and deployers) and attackers (malicious actors, misaligned contributors, or worst-case failure modes), SSGs provide a unifying framework for reasoning about incentive design, limited oversight capacity, and adversarial uncertainty across the AI lifecycle. We illustrate how this framework can inform 1) training-time auditing against data/feedback poisoning, 2) pre-deployment evaluation under constrained reviewer resources, and 3) robust multimodel deployment in adversarial environments. This synthesis bridges algorithmic alignment and institutional oversight design.