FheFL: Fully Homomorphic Encryption Friendly Privacy-Preserving Federated Learning with Byzantine Users

no code implementations • 8 Jun 2023 • Yogachandran Rahulamathavan, Charuka Herath, Xiaolan Liu, Sangarapillai Lambotharan, Carsten Maple

We also develop a novel aggregation scheme within the encrypted domain, utilizing users' non-poisoning rates, to effectively address data poisoning attacks while ensuring privacy is preserved by the proposed encryption scheme.

Data Poisoning Federated Learning +1

Recursive Euclidean Distance Based Robust Aggregation Technique For Federated Learning

no code implementations • 20 Mar 2023 • Charuka Herath, Yogachandran Rahulamathavan, Xiaolan Liu

However, the aggregation process of local model updates to obtain a global model in federated learning is susceptible to malicious attacks, such as backdoor poisoning, label-flipping, and membership inference.

Data Poisoning Federated Learning