FADE: Enabling Federated Adversarial Training on Heterogeneous Resource-Constrained Edge Devices

Understand

Federated adversarial training can effectively complement adversarial robustness into the privacy-preserving federated learning systems.

• However, the high demand for memory capacity and computing power makes large-scale federated adversarial training infeasible on resource-constrained edge devices.
• Few previous studies in federated adversarial training have tried to tackle both memory and computational constraints simultaneously.
• In this paper, we propose a new framework named Federated Adversarial Decoupled Learning (FADE) to enable AT on heterogeneous resource-constrained edge devices.