Beyond Traditional Threats: A Persistent Backdoor Attack on Federated Learning

arXiv:2404.17617v1 Announce Type: cross
Abstract: Backdoors on federated learning will be diluted by subsequent benign updates. This is reflected in the significant reduction of attack success rate as iterations increase, ultimately failing. We use a new metric to quantify the degree of this weakened backdoor effect, called attack persistence. Given that research to improve this performance has not been widely noted,we propose a Full Combination Backdoor Attack (FCBA) method. It aggregates more combined trigger information for a more complete backdoor …

arxiv backdoor beyond cs.ai cs.cr cs.cv cs.lg federated learning threats type