A Survey on Federated Learning Poisoning Attacks and Defenses. (arXiv:2306.03397v1 [cs.CR])

As one kind of distributed machine learning technique, federated learning
enables multiple clients to build a model across decentralized data
collaboratively without explicitly aggregating the data. Due to its ability to
break data silos, federated learning has received increasing attention in many
fields, including finance, healthcare, and education. However, the invisibility
of clients' training data and the local training process result in some
security issues. Recently, many works have been proposed to research the
security attacks and defenses in federated …

attacks attention build clients data data silos decentralized decentralized data distributed education federated learning finance healthcare machine machine learning poisoning poisoning attacks silos survey