arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.00342cs.LGcs.CR
收藏

联邦学习中的隐私威胁与对策综述

Survey of Privacy Threats and Countermeasures in Federated Learning

Secure System Platform Research Laboratories, NEC Corporation(NEC公司安全系统平台研究实验室)

Masahiro Hayashitani, Junki Mori, Isamu Teranishi

AI总结:

本文综述横向、纵向和迁移联邦学习中的隐私威胁及防护对策,弥补现有研究对不同类型联邦学习共性与特有威胁缺乏系统分类的不足。

摘要:

联邦学习被广泛认为是一种具有隐私意识的学习方法,因为客户端之间不会直接交换训练数据。尽管如此,联邦学习中仍存在隐私威胁,且隐私对策已得到研究。然而,我们注意到,典型联邦学习类型之间共同且独特的隐私威胁尚未得到全面而具体的分类与描述。本文描述了横向联邦学习、纵向联邦学习和迁移联邦学习这三类典型联邦学习的隐私威胁与对策。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑