RoFL: Robustness of Secure Federated Learning
RoFL: Robustness of Secure Federated Learning
Even though recent years have seen many attacks exposing severe vulnerabilities in Federated Learning (FL), a holistic understanding of what enables these attacks and how they can be mitigated effectively is still lacking. In this work, we demystify the inner workings of existing (targeted) attacks. We provide new insights into …