Suchul Lee, Journal of Internet Computing and Services, Vol. 25, No. 2, pp. 1-9, Apr. 2024
10.7472/jksii.2024.25.2.1, Full Text:  HTML
Keywords: Federated learning, adversarial attacks, adversarial training, trade-off relationship

Abstract

Although federated learning is designed to be safer than centralized methods in terms of security and privacy, it still has many vulnerabilities. An attacker performing an adversarial attack intentionally manipulates the deep learning model by injecting carefully crafted input data, that is, adversarial examples, into the client's training data to induce misclassification. A common defense strategy against this is so-called adversarial training, which involves preemptively learning the characteristics of adversarial examples into the model. Existing research assumes a scenario where all clients are under adversarial attack, but considering the number of clients in federated learning is very large, this is far from reality. In this paper, we experimentally examine aspects of adversarial training in a scenario where some of the clients are under attack. Through experiments, we found that there is a trade-off relationship in which the classification accuracy for normal samples decreases as the classification accuracy for adversarial examples increases. In order to effectively utilize this trade-off relationship, we present a method to perform adversarial training by adaptively selecting a loss function depending on whether the client is attacked.

Statistics
Cite this article