Survey of Privacy Threats and Countermeasures in Federated Learning

Autor:	Hayashitani, Masahiro, Mori, Junki, Teranishi, Isamu
Rok vydání:	2024
Předmět:	Computer Science - Machine Learning Computer Science - Cryptography and Security
Druh dokumentu:	Working Paper
Popis:	Federated learning is widely considered to be as a privacy-aware learning method because no training data is exchanged directly between clients. Nevertheless, there are threats to privacy in federated learning, and privacy countermeasures have been studied. However, we note that common and unique privacy threats among typical types of federated learning have not been categorized and described in a comprehensive and specific way. In this paper, we describe privacy threats and countermeasures for the typical types of federated learning; horizontal federated learning, vertical federated learning, and transfer federated learning. Comment: Scheduled for renewal by March 2024
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2402.00342 Zobrazit plný text záznamu View this record from Arxiv