Biblio Discovery — Demo Discovery Service

1 results for "Ridowan, Muhammad"

Showing 1–1 · 0.21 seconds · RSS

  1. Preprint Full text

    XFED: Non-Collusive Model Poisoning Attack Against Byzantine-Robust Federated Classifiers

    Mouri, Israt Jahan; Ridowan, Muhammad; Adnan, Muhammad Abdullah

    arXiv · 2026 · English · arXiv

    Model poisoning attacks pose a significant security threat to Federated Learning (FL). Most existing model poisoning attacks rely on collusion, requiring adversarial clients to coordinate by exchanging local benign models and synchronizing the generation of their poisoned updates. However…