<ul><li>Federated Learning is vulnerable to model poisoning attacks due to its distributed nature.</li><li>Existing defenses against model poisoning attacks assume the data at remote clients are under iid, while in practice they are non-iid.</li><li>GeminiGuard is a novel defense approach that addresses the gap in non-iid scenarios.</li><li>GeminiGuard incorporates model-weight analysis and latent-space analysis to enhance defense performance.</li></ul>

Two Heads Are Better than One: Model-Weight and Latent-Space Analysis for Federated Learning on Non-iid Data against Poisoning Attacks

Discover more