FedDefender: Backdoor Attack Defense in Federated Learning

arXiv:2307.08672v2 Announce Type: replace
Abstract: Federated Learning (FL) is a privacy-preserving distributed machine learning technique that enables individual clients (e.g., user participants, edge devices, or organizations) to train a model on their local data in a secure environment and then share the trained model with an aggregator to build a global model collaboratively. In this work, we propose FedDefender, a defense mechanism against targeted poisoning attacks in FL by leveraging differential testing. Our proposed method fingerprints the neuron activations of …

arxiv attack backdoor build clients cs.ai cs.cr cs.cv cs.lg data defense devices distributed edge edge devices environment federated federated learning global local machine machine learning organizations privacy share train