FL-MAC-RDP: Federated Learning over Multiple Access Channels with Rényi Differential Privacy

Wu, Shuhui; Yu, Mengqing; Ahmed, Moushira Abdallah Mohamed; Qian, Yaguan; Tao, Yuan-Hong

doi:10.1007/s10773-021-04867-0

Cited by 8 publications

(1 citation statement)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A large amount of individual data have aggregated for computing various statistics, query responses, classifiers, and other functions. However, these processes will release sensitive information compromising individual privacy [ 97 , 98 , 99 , 100 ]. Thus, when considering the aggregation of multiuser data, the GDP and LDP mechanisms need to be studied from the multiple access channel.…”

Section: Open Problemsmentioning

confidence: 99%

GDP vs. LDP: A Survey from the Perspective of Information-Theoretic Channel

Liu

Peng

Tian

et al. 2022

Entropy

View full text Add to dashboard Cite

The existing work has conducted in-depth research and analysis on global differential privacy (GDP) and local differential privacy (LDP) based on information theory. However, the data privacy preserving community does not systematically review and analyze GDP and LDP based on the information-theoretic channel model. To this end, we systematically reviewed GDP and LDP from the perspective of the information-theoretic channel in this survey. First, we presented the privacy threat model under information-theoretic channel. Second, we described and compared the information-theoretic channel models of GDP and LDP. Third, we summarized and analyzed definitions, privacy-utility metrics, properties, and mechanisms of GDP and LDP under their channel models. Finally, we discussed the open problems of GDP and LDP based on different types of information-theoretic channel models according to the above systematic review. Our main contribution provides a systematic survey of channel models, definitions, privacy-utility metrics, properties, and mechanisms for GDP and LDP from the perspective of information-theoretic channel and surveys the differential privacy synthetic data generation application using generative adversarial network and federated learning, respectively. Our work is helpful for systematically understanding the privacy threat model, definitions, privacy-utility metrics, properties, and mechanisms of GDP and LDP from the perspective of information-theoretic channel and promotes in-depth research and analysis of GDP and LDP based on different types of information-theoretic channel models.

show abstract

Section: Open Problemsmentioning

confidence: 99%

GDP vs. LDP: A Survey from the Perspective of Information-Theoretic Channel

Liu

Peng

Tian

et al. 2022

Entropy

View full text Add to dashboard Cite

show abstract

Mobile health‐empowered traditional ethnic sports: AI‐based data analysis improving security

Liu

Jin

2023

Internet Technology Letters

View full text Add to dashboard Cite

Traditional ethnic sports shape the Chinese nation's solid national spirit, and mobile health development has been extended to various fields. In this study, we empower mobile health to traditional ethnic sports. Sensors used for collecting health data are worn on athletes and communicated with sink nodes through the network to provide better training guidance for traditional ethnic sports athletes through data analysis. However, the devices used to collect health data may come from many companies, and aggregating the data inevitably involves data security. As a new basic artificial intelligence technology, federated learning can use the health data of athletes to train the data analysis model in the case of original data localization, to solve the security and privacy problems in health data sharing to a certain extent. To this end, a differentially private‐dynamic federated learning framework for dynamic aggregation weights under an untrusted central server is proposed, which sets a dynamic model aggregation weight, and this method directly learns federated learning from the data of different participants. The learning model aggregates the weights so that it is suitable for non‐independent data environments. Experimental results show that the proposed framework not only provides local privacy guarantees, but also achieves higher accuracy and improves the security of mobile health data of traditional ethnic sports athletes in federated learning.

show abstract

An overview of implementing security and privacy in federated learning

Hu,

Gong,

Zhang

et al. 2024

Artif Intell Rev

View full text Add to dashboard Cite

Federated learning has received a great deal of research attention recently,with privacy protection becoming a key factor in the development of artificial intelligence. Federated learning is a special kind of distributed learning framework, which allows multiple users to participate in model training while ensuring that their privacy is not compromised; however, this paradigm is still vulnerable to security and privacy threats from various attackers. This paper focuses on the security and privacy threats related to federated learning. First, we analyse the current research and development status of federated learning through use of the CiteSpace literature search tool. Next, we describe the basic concepts and threat models, and then analyse the security and privacy vulnerabilities within current federated learning architectures. Finally, the directions of development in this area are further discussed in the context of current advanced defence solutions, for which we provide a summary and comparison.

show abstract

FL-MAC-RDP: Federated Learning over Multiple Access Channels with Rényi Differential Privacy

Cited by 8 publications

References 31 publications

GDP vs. LDP: A Survey from the Perspective of Information-Theoretic Channel

GDP vs. LDP: A Survey from the Perspective of Information-Theoretic Channel

Mobile health‐empowered traditional ethnic sports: AI‐based data analysis improving security

An overview of implementing security and privacy in federated learning

Contact Info

Product

Resources

About