End-to-End Game-Focused Learning of Adversary Behavior in Security Games
This work addresses a domain-specific problem in green security for defenders needing to generalize to new targets with limited data, representing an incremental improvement over existing methods.
The paper tackles the problem of learning adversary behavior in security games with limited data, where traditional two-stage methods train adversary models for predictive accuracy without considering the defender's optimization. The result is that their end-to-end game-focused approach achieves higher defender expected utility than the two-stage alternative, as shown in theory and experiments.
Stackelberg security games are a critical tool for maximizing the utility of limited defense resources to protect important targets from an intelligent adversary. Motivated by green security, where the defender may only observe an adversary's response to defense on a limited set of targets, we study the problem of learning a defense that generalizes well to a new set of targets with novel feature values and combinations. Traditionally, this problem has been addressed via a two-stage approach where an adversary model is trained to maximize predictive accuracy without considering the defender's optimization problem. We develop an end-to-end game-focused approach, where the adversary model is trained to maximize a surrogate for the defender's expected utility. We show both in theory and experimental results that our game-focused approach achieves higher defender expected utility than the two-stage alternative when there is limited data.