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.
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.