An efficient approach for privacy preserving decentralized deep learning models based on secure multi-party computation

Tran, Anh-Tu Ngoc; Luong, The-Dung; Karnjana, Jessada; Huynh, Van–Nam

doi:10.1016/j.neucom.2020.10.014

Cited by 58 publications

(21 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Finally, the user gives feedback and saves it through the key. Different mathematical tools can be employed to construct the secret sharing scheme of threshold thresholds, which mainly consists of two phases: underground distribution and secret reconstruction (Tran et al, 2021). First, the secret distributor generates sub-secrets and sends them to the participant set.…”

Section: Related Technologiesmentioning

confidence: 99%

Optimization of Digital Information Management of Financial Services Based on Artificial Intelligence in the Digital Financial Environment

Zhang

Long

et al. 2023

Journal of Organizational and End User Computing

View full text Add to dashboard Cite

At present, society has entered the era of digital finance, and the information management system (IMS) of financial services has been developing rapidly, so the security of data has become particularly important. Firstly, some security techniques in IMS of financial services are introduced. Secondly, this study analyzes how to combine secure muti-party computation with blockchain technology to enhance the security of IMS. Finally, the feasibility and reliability of the scheme are verified by a comparative test. The experimental results reveal that the evaluation index score of the optimized scheme is higher than that of the traditional scheme. Meanwhile, in the comparative experiment of information data encryption, it can be seen that the running time of all schemes will improve with the increase of data. However, the increase rate of the optimized model in this study is much slower than that of the traditional model.

show abstract

Section: Related Technologiesmentioning

confidence: 99%

Optimization of Digital Information Management of Financial Services Based on Artificial Intelligence in the Digital Financial Environment

Zhang

Long

et al. 2023

Journal of Organizational and End User Computing

View full text Add to dashboard Cite

show abstract

“…Tran et al [119] propose a framework, called Secure Decentralized Training Framework (SDTF), to protect the privacy of clients participating in training a decentralized FL. The clients train a model without a server, however, at each epoch, they elect a master node (one of them) which calculates the global gradient and sends it to all nodes, and so on until the algorithm converges.…”

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

“…Tran et al proposed an efficient framework for privacypreserving deep neural networks. This framework is not only capable of training deep learning models at high speed but is also highly resistant to collusion attacks [21].…”

Section: Secure Computation Of Sensitive Datamentioning

confidence: 99%

Re-Identification in Differentially Private Incomplete Datasets

Sei

Okumura

Ohsuga

2022

IEEE Open J. Comput. Soc.

View full text Add to dashboard Cite

Efforts to counter COVID-19 reaffirmed the importance of rich medical, behavioral, and sociological data. To make data available to many researchers who can conduct statistical analyses and machine learning, personally identifiable information must be excluded to protect individual privacy. It is essential to remove explicit identifiers, sample population data, and apply differential privacy, the de facto standard privacy metric. Despite the general belief that the risk of re-identification is insignificant when these techniques are applied, this study shows that even after applying these techniques, the risk of being re-identified is highly significant for some data. This study proposes in detail an algorithm for estimating the number of people in a population who have certain attribute values based on incomplete, differentially private databases. If the estimated number is one, the probability that only one person with that attribute value is present in the population is high, which means that there is a high probability of re-identification. Therefore, this study concludes that the re-identification risk must be evaluated even after applying state-of-the-art techniques to protect privacy.INDEX TERMS Differential privacy, ethical and privacy framework, re-identification.

show abstract

An efficient approach for privacy preserving decentralized deep learning models based on secure multi-party computation

Cited by 58 publications

References 38 publications

Optimization of Digital Information Management of Financial Services Based on Artificial Intelligence in the Digital Financial Environment

Optimization of Digital Information Management of Financial Services Based on Artificial Intelligence in the Digital Financial Environment

Differential Privacy for Deep and Federated Learning: A Survey

Re-Identification in Differentially Private Incomplete Datasets

Contact Info

Product

Resources

About