Strategic federated learning improves defense against covert attacks
StratFL: Countering Covert Model Poisoning Attacks with Strategic Federated Learning
Cryptography and SecurityArtificial IntelligenceComputer Science and Game Theory
Summary
Federated learning allows many users to train AI models together without sharing their data, but attackers can secretly corrupt the shared model updates, making it less accurate. This paper studies a sneaky kind of attack where bad updates happen only sometimes, which traditional defenses miss. The authors model the interaction between the defender and attacker as a game where neither side fully sees the other's moves, and create a new method called StratFL that strategically detects and counters these hidden attacks. Tests show StratFL achieves about 10% better accuracy than other leading methods on common image datasets.
What this means in practice
- •For healthcare ai teams: Protect federated learning systems in medical settings from stealthy model corruption attacks that degrade AI accuracy over time.
- •For financial technology developers: Enhance fraud detection and risk models trained via federated learning by mitigating intermittent poisoned updates in critical financial applications.
Authors
Manoj Twarakavi, Venkata Sriram Siddhardh Nadendla
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.