TrajSyn: Privacy-Preserving Dataset Distillation from Federated Model Trajectories for Server-Side Adversarial Training

Deep learning models deployed on edge devices are increasingly used in safety-critical applications. However, their vulnerability to adversarial perturbations poses significant risks, especially in Federated Learning (FL) settings where identical models are distributed across thousands of clients. While adversarial training is a strong defense, it is difficult to apply in FL due to strict client-data privacy constraints and the limited compute available on edge devices. In this work, we introduce TrajSyn, a privacy-preserving framework that enables effective server-side adversarial training by synthesizing a proxy dataset from the trajectories of client model updates, without accessing raw client data. We show that TrajSyn consistently improves adversarial robustness on image classification benchmarks with no extra compute burden on the client device.

Key Contributions

• TrajSyn framework that synthesizes a privacy-preserving proxy dataset from client model update trajectories (without accessing raw client data), enabling server-side adversarial training in federated learning
• Demonstration that server-side adversarial training on synthesized trajectory-derived data consistently improves adversarial robustness on image classification benchmarks
• Zero additional computational overhead on client devices — the adversarial training burden is fully offloaded to the server

🛡️ Threat Analysis

Details

Similar Papers