DarkFed: A Data-Free Backdoor Attack in Federated Learning

arXiv:2405.03299v1 Announce Type: new
Abstract: Federated learning (FL) has been demonstrated to be susceptible to backdoor attacks. However, existing academic studies on FL backdoor attacks rely on a high proportion of real clients with main task-related data, which is impractical. In the context of real-world industrial scenarios, even the simplest defense suffices to defend against the state-of-the-art attack, 3DFed. A practical FL backdoor attack remains in a nascent stage of development.
To bridge this gap, we present DarkFed. Initially, we …

academic arxiv attack attacks backdoor backdoor attack backdoor attacks clients context cs.cr cs.dc data defense federated federated learning free high industrial main real studies task world