DeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model Inspection. (arXiv:2201.00763v1 [cs.CR])

Federated Learning (FL) allows multiple clients to collaboratively train a
Neural Network (NN) model on their private data without revealing the data.
Recently, several targeted poisoning attacks against FL have been introduced.
These attacks inject a backdoor into the resulting model that allows
adversary-controlled inputs to be misclassified. Existing countermeasures
against backdoor attacks are inefficient and often merely aim to exclude
deviating models from the aggregation. However, this approach also removes
benign models of clients with deviating data distributions, causing …

attacks backdoor