<ul><li>Researchers propose a new aggregation scheme, Layerwise Cosine Aggregation, to enhance the robustness of Federated Learning (FL) systems against Byzantine attacks.</li><li>FL is a privacy-preserving approach for distributed machine learning, but it is vulnerable to malicious nodes contributing corrupted model updates.</li><li>Layerwise Cosine Aggregation improves the performance of robust aggregation operators in high-dimensional parameter spaces, leading to up to a 16% increase in model accuracy.</li><li>Theoretical analysis and empirical evaluation across various image classification datasets validate the superior robustness of Layerwise Cosine Aggregation.</li></ul>

Improving $(\alpha, f)$-Byzantine Resilience in Federated Learning via layerwise aggregation and cosine distance

Discover more