Concealing Backdoor Model Updates in Federated Learning by Trigger-Optimized Data Poisoning

arXiv:2405.06206v1 Announce Type: new
Abstract: Federated Learning (FL) is a decentralized machine learning method that enables participants to collaboratively train a model without sharing their private data. Despite its privacy and scalability benefits, FL is susceptible to backdoor attacks, where adversaries poison the local training data of a subset of clients using a backdoor trigger, aiming to make the aggregated model produce malicious results when the same backdoor condition is met by an inference-time input. Existing backdoor attacks in FL …

adversaries arxiv attacks backdoor backdoor attacks benefits cs.ai cs.cr cs.lg data data poisoning decentralized federated federated learning local machine machine learning poisoning privacy private private data scalability sharing train training training data trigger updates