<ul><li>Federated learning (FL) enables training a shared model without transmitting private data to a central server.</li><li>FL is vulnerable to Byzantine attacks from compromised edge devices, degrading model performance.</li><li>The proposed plugin integrates into existing FL techniques to achieve Byzantine resilience.</li><li>By generating virtual data samples and evaluating model consistency scores, compromised devices can be filtered out, maintaining the benefits of FL.</li></ul>

Embedding Byzantine Fault Tolerance into Federated Learning via Consistency Scoring

Discover more