Federated Learning with Privacy-preserving and Model IP-right-protection

doi:10.1007/s11633-022-1343-2

CASIA OpenIR > 学术期刊 > Machine Intelligence Research

	Federated Learning with Privacy-preserving and Model IP-right-protection
	Qiang Yang 1,2
发表期刊	Machine Intelligence Research
ISSN	2731-538X
	2023
卷号	20 期号:1 页码:19-37
摘要	In the past decades, artificial intelligence (AI) has achieved unprecedented success, where statistical models become the central entity in AI. However, the centralized training and inference paradigm for building and using these models is facing more and more privacy and legal challenges. To bridge the gap between data privacy and the need for data fusion, an emerging AI paradigm federated learning (FL) has emerged as an approach for solving data silos and data privacy problems. Based on secure distributed AI, federated learning emphasizes data security throughout the lifecycle, which includes the following steps: data preprocessing, training, evaluation, and deployments. FL keeps data security by using methods, such as secure multi-party computation (MPC), differential privacy, and hardware solutions, to build and use distributed multiple-party machine-learning systems and statistical models over different data sources. Besides data privacy concerns, we argue that the concept of “model” matters, when developing and deploying federated models, they are easy to expose to various kinds of risks including plagiarism, illegal copy, and misuse. To address these issues, we introduce FedIPR, a novel ownership verification scheme, by embedding watermarks into FL models to verify the ownership of FL models and protect model intellectual property rights (IPR or IP-right for short). While security is at the core of FL, there are still many articles referred to distributed machine learning with no security guarantee as “federated learning”, which are not satisfied with the FL definition supposed to be. To this end, in this paper, we reiterate the concept of federated learning and propose secure federated learning (SFL), where the ultimate goal is to build trustworthy and safe AI with strong privacy-preserving and IP-right-preserving. We provide a comprehensive overview of existing works, including threats, attacks, and defenses in each phase of SFL from the lifecycle perspective.
关键词	Federated learning privacy-preserving machine learning security decentralized learning intellectual property protection
DOI	10.1007/s11633-022-1343-2
引用统计	被引频次：3[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/50898
专题	学术期刊_Machine Intelligence Research
作者单位	1.WeBank, Shenzhen 518057, China 2.Hong Kong University of Science and Technology, Hong Kong 999077, China 3.University of Malaya, Kuala Lumpur 50603, Malaysia 4.University of Surrey, Guildford GU2 7XH, UK 5.University of Aberystwyth, Wales SY23 3DD, UK 6.Shanghai Jiao Tong University, Shanghai 200240, China
推荐引用方式 GB/T 7714	Qiang Yang. Federated Learning with Privacy-preserving and Model IP-right-protection[J]. Machine Intelligence Research,2023,20(1):19-37.
APA	Qiang Yang.(2023).Federated Learning with Privacy-preserving and Model IP-right-protection.Machine Intelligence Research,20(1),19-37.
MLA	Qiang Yang."Federated Learning with Privacy-preserving and Model IP-right-protection".Machine Intelligence Research 20.1(2023):19-37.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
MIR-2022-03-072.pdf（2634KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载