Privacy-Preserving Federated Learning Framework Based on Chained Secure Multiparty Computing

Li, Yong; Zhou, Yipeng; Jolfaei, Alireza; Yu, Dongjin; Xu, Gaochao; Zheng, Xi

doi:10.1109/jiot.2020.3022911

Cited by 164 publications

(57 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The experimental results show that the proposed system is beneficial for saving the energy of IoT devices and security analysis suggests that the differential privacy technique can protect against sensitive health data from being obtained maliciously. In our future work, we will investigate how to incorporate highly efficient blockchain and federated learning techniques [ 19 , 30 ] into our solution in order to improve privacy preservation while maintaining high accuracy in the data inferencing system.…”

Section: Discussionmentioning

confidence: 99%

“…The authors claimed that the proposed scheme could achieve higher processing efficiency when compared to traditional location privacy protection algorithms. Another privacy-preserving framework for exchanging gradients in federated learning with chained secure multi-part computing technique is proposed in Li et al [ 19 ]. The authors argued that the proposed approach is equivalent to differential privacy when E = 0, which prevents sensitive information leakage (e.g., gradients).…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

An Energy-Efficient and Secure Data Inference Framework for Internet of Health Things: A Pilot Study

Kang

Dibaei

Luo

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

Privacy protection in electronic healthcare applications is an important consideration, due to the sensitive nature of personal health data. Internet of Health Things (IoHT) networks that are used within a healthcare setting have unique challenges and security requirements (integrity, authentication, privacy, and availability) that must also be balanced with the need to maintain efficiency in order to conserve battery power, which can be a significant limitation in IoHT devices and networks. Data are usually transferred without undergoing filtering or optimization, and this traffic can overload sensors and cause rapid battery consumption when interacting with IoHT networks. This poses certain restrictions on the practical implementation of these devices. In order to address these issues, this paper proposes a privacy-preserving two-tier data inference framework solution that conserves battery consumption by inferring the sensed data and reducing data size for transmission, while also protecting sensitive data from leakage to adversaries. The results from experimental evaluations on efficiency and privacy show the validity of the proposed scheme, as well as significant data savings without compromising data transmission accuracy, which contributes to energy efficiency of IoHT sensor devices.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

An Energy-Efficient and Secure Data Inference Framework for Internet of Health Things: A Pilot Study

Kang

Dibaei

Luo

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Li et al [120] propose a privacy-preserving FL framework based on secure multiparty computing called chain-PPFL. This approach is similar to [31], except that here the authors are based on the principle of secure multiparty computing instead of DP.…”

Section: Main Contributionmentioning

confidence: 99%

Differential Privacy for Deep and Federated Learning: A Survey

2022

View full text Add to dashboard Cite

Users' privacy is vulnerable at all stages of the deep learning process. Sensitive information of users may be disclosed during data collection, or during training, or even after releasing the trained learning model. Differential privacy (DP) is one of the main approaches proven to ensure strong privacy protection in data analysis. DP protects the users' privacy by adding noise to the original dataset or the learning parameters. Thus, an attacker could not retrieve the sensitive information of an individual involved in the training dataset. In this survey paper, we analyze and present the main ideas based on DP to guarantee users' privacy in deep and federated learning. In addition, we illustrate all types of probability distributions that satisfy the DP mechanism, with their properties and use cases. Furthermore, we bridge the gap in the literature by providing a comprehensive overview of the different variants of DP, highlighting their advantages and limitations. Our study reveals the gap between theory and application, accuracy, and robustness of DP. Finally, we provide several open problems and future research directions.

show abstract

“…Collaborative Learning with Secure Muti-Party Computation. Another widely applied cryptographic method is secure multi-party computation (SMC), which allows mutual distrust participants to jointly compute a function over their inputs and preserve the privacy of inputs [65], [66], [174], [175]. Bonawitz et al [65] proposed a communicationefficient, failure-robust secure aggregation of high dimensional model updates without learning each participant's sensitive information with SMC, which can defense both passive and active adversaries.…”

Section: B Cryptographic Privacy-preserving Collaborative Learningmentioning

confidence: 99%

“…To address the above integrity and privacy threats, many methods are proposed to defend these attacks [24], [26], [28], [35]- [48], [48], [49], [49]- [66]. For instance, to achieve byzantine-resilient collaborative learning, Blanchard et al [28] use statistic tools to inspect the updates of participants at each iteration and abandon potential malicious updates when aggregating updates.…”

Section: Introductionmentioning

confidence: 99%

Robust and Privacy-Preserving Collaborative Learning: A Comprehensive Survey

Guo¹,

Zhang²,

Yang³

et al. 2021

Preprint

View full text Add to dashboard Cite

With the rapid demand of data and computational resources in deep learning systems, a growing number of algorithms to utilize collaborative machine learning techniques, for example, federated learning, to train a shared deep model across multiple participants. It could effectively take advantage of resource of each participant and obtain a more powerful learning system. However, integrity and privacy threats in such systems have greatly obstructed the applications of collaborative learning. And a large amount of works have been proposed to maintain the model integrity and mitigate the privacy leakage of training data during the training phase for different collaborate learning systems. Compared with existing surveys that mainly focus on one specific collaborate learning system, this survey aims to provide a systematic and comprehensive review of security and privacy researches in collaborative learning. Our survey first provides the system overview of collaborative learning, followed by an brief introduction of integrity and privacy threats. In an organized way, we then detail the existing integrity and privacy attacks as well as their defenses. We also list some open problems in this area and opensource the related papers on GitHub: https://github.com/csl-cqu/awesome-secure-collebrativelearning-papers.

show abstract

Privacy-Preserving Federated Learning Framework Based on Chained Secure Multiparty Computing

Cited by 164 publications

References 22 publications

An Energy-Efficient and Secure Data Inference Framework for Internet of Health Things: A Pilot Study

An Energy-Efficient and Secure Data Inference Framework for Internet of Health Things: A Pilot Study

Differential Privacy for Deep and Federated Learning: A Survey

Robust and Privacy-Preserving Collaborative Learning: A Comprehensive Survey

Contact Info

Product

Resources

About