Privacy protection against attack scenario of federated learning using internet of things
Kusum Yadav, Elham Kariri, Shoayee Dlaim Alotaibi, Wattana Viriyasitavat, Gaurav Dhiman, Amandeep Kaur
Abstract
Laws and regulations for privacy protection have been promulgated one after another, and the phenomenon of data islands has become a significant bottleneck hindering the development of big data and artificial intelligence technologies. From the perspective of the historical development, concepts, and architecture classification of federated learning, the technical advantages of federated learning are explained using Internet of Things. Simultaneously, numerous attack methods and classifications of federated learning systems are examined, as well as the distinctions between different federated learning encryption algorithms. Finally, it reviews research in the subject of federal learning privacy protection and security mechanisms, as well as identifies difficulties and opportunities.