Blockchain-Based Privacy Preserving Deep Learning

Zhu, Xudong; Li, Hui; Yu, Yang

doi:10.1007/978-3-030-14234-6_20

Cited by 31 publications

(20 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although the machine learning techniques dramatically enhance the performance of mobile applications, traditional machine learning techniques require mobile devices to directly upload user data with potentially sensitive private information to a central server for model training [2]. This causes not only large computation and storage overhead, but also serious risk of privacy breach due to the centralized entity suffering from single point of failure [3]. To solve these challenges, an emerging distributed machine learning technique named federated learning is introduced to allow mobile devices to jointly train a shared global model in a decentralized manner.…”

Section: Introductionmentioning

confidence: 99%

Incentive Design for Efficient Federated Learning in Mobile Networks: A Contract Theory Approach

Kang

Xiong

Niyato

et al. 2019

2019 IEEE VTS Asia Pacific Wireless Communications Symposium (APWCS)

182

101

View full text Add to dashboard Cite

To strengthen data privacy and security, federated learning as an emerging machine learning technique is proposed to enable large-scale nodes, e.g., mobile devices, to distributedly train and globally share models without revealing their local data. This technique can not only significantly improve privacy protection for mobile devices, but also ensure good performance of the trained results collectively. Currently, most the existing studies focus on optimizing federated learning algorithms to improve model training performance. However, incentive mechanisms to motivate the mobile devices to join model training have been largely overlooked. The mobile devices suffer from considerable overhead in terms of computation and communication during the federated model training process. Without well-designed incentive, self-interested mobile devices will be unwilling to join federated learning tasks, which hinders the adoption of federated learning. To bridge this gap, in this paper, we adopt the contract theory to design an effective incentive mechanism for simulating the mobile devices with high-quality (i.e., high-accuracy) data to participate in federated learning. Numerical results demonstrate that the proposed mechanism is efficient for federated learning with improved learning accuracy.

show abstract

Section: Introductionmentioning

confidence: 99%

Incentive Design for Efficient Federated Learning in Mobile Networks: A Contract Theory Approach

Kang

Xiong

Niyato

et al. 2019

2019 IEEE VTS Asia Pacific Wireless Communications Symposium (APWCS)

182

101

View full text Add to dashboard Cite

show abstract

“…Besides, promising future work in the privacy-preserving deep learning approach, particularly in the context of collaborative or federated model learning, might also involve further exploration of the Blockchain technology, one of the emerging technologies nowadays. Blockchain, initially used in the financial industry, is basically a peer-to-peer distributed ledger technology or database represented by a series of data blocks secured and linked using cryptography [44][45][46]. In the literature, some Blockchain-related works addressing privacy-preservation in deep learning [44][45][46][47][48] have already been conducted.…”

Section: Future Directionsmentioning

confidence: 99%

“…Blockchain, initially used in the financial industry, is basically a peer-to-peer distributed ledger technology or database represented by a series of data blocks secured and linked using cryptography [44][45][46]. In the literature, some Blockchain-related works addressing privacy-preservation in deep learning [44][45][46][47][48] have already been conducted. Jiasi Weng et al [47] for example presented "Deepchain" a secure framework for distributed deep learning introducing a value-driven incentive mechanism based on Blockchain in order to address malicious adversaries as well as the lack of incentives for distrustful participants.…”

Section: Future Directionsmentioning

confidence: 99%

A review of privacy-preserving techniques for deep learning

2020

View full text Add to dashboard Cite

Deep learning is one of the advanced approaches of machine learning, and has attracted a growing attention in the recent years. It is used nowadays in different domains and applications such as pattern recognition, medical prediction, and speech recognition. Differently from traditional learning algorithms, deep learning can overcome the dependency on hand-designed features. Deep learning experience is particularly improved by leveraging powerful infrastructures such as clouds and adopting collaborative learning for model training. However, this comes at the expense of privacy, especially when sensitive data are processed during the training and the prediction phases, as well as when training model is shared. In this paper, we provide a review of the existing privacy-preserving deep learning techniques, and propose a novel multilevel taxonomy, which categorizes the current state-of-the-art privacy-preserving deep learning techniques on the basis of privacy-preserving tasks at the top level, and key technological concepts at the base level. This survey further summarizes evaluation results of the reviewed solutions with respect to defined performance metrics. In addition, it derives a set of learned lessons from each privacy-preserving task. Finally, it highlights open research challenges and provides some recommendations as future research directions.

show abstract

“…Zhu et al proposed a blockchain-enabled decentralized ML platform to eliminate malfunctioning nodes that negatively influence the model update [11]. The global ML model is repeatedly updated.…”

Section: Related Workmentioning

confidence: 99%