StratFL: Countering Covert Model Poisoning Attacks with Strategic Federated Learning
StratFL is a federated learning defense against covert model poisoning, where an attacker behaves like an APT by only occasionally sending poisoned updates, and the server–attacker interaction is framed as an imperfect-information repeated game with neither side directly observing the other’s actions. The interesting bit is the strategic belief-updating plus adversarial-search approach, which reportedly beats prior defenses by about 10% accuracy on MNIST/CIFAR-10, though the evidence seems limited to relatively standard benchmark simulations rather than messy real-world FL deployments or stronger adaptive attack studies.
Abstract
Advanced persistent threats (APTs) are a major concern in federated learning (FL) deployments in critical sectors such as healthcare, and finance. Traditional defense mechanisms fail to contain APTs due to their intermittent attacking behavior. This paper addresses a specific type of APT called covert model poisoning (CMP) where the attacker intermittently injects poisoned model updates in a covert manner. The interaction between the FL server and a CMP attacker is modeled as an imperfect repeated game where both players cannot observe each other's actions. A novel adversarial search algorithm called StratFL is designed alongside novel belief update algorithms at both the server and adversary. Experiments are designed using MNIST and CIFAR-10 datasets to evaluate and compare StratFL's performance against state-of-the-art methods. Empirical convergence of belief update algorithms is demonstrated across various security vignettes. At the same time, StratFL is found to exhibit an improved accuracy of 10% compared to state-of-the-art methods.