Privacy-Preserving distributed deep learning based on secret sharing

Duan, Jia; Zhou, Jiantao; Li, Yuanman

doi:10.1016/j.ins.2020.03.074

Cited by 40 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the existing federated learning mostly relies on the central server to generate global model parameters, which is a centralized architecture, which has problems such as single point of failure, privacy leakage, and performance bottlenecks. In order to solve the above problems, some scholars use encryption methods such as homomorphic encryption [2][3][4][5] and secure multiparty computing [6][7][8][9] to encrypt model parameters sent by participants to resist model inference attacks. Another part of scholars proposed the method of differential privacy [10,11], which makes it difficult for attackers to infer the original model parameters by adding disturbance noise to the model parameters.…”

Section: Introductionmentioning

confidence: 99%

AFLPC: An Asynchronous Federated Learning Privacy-Preserving Computing Model Applied to 5G-V2X

Huang

et al. 2022

Security and Communication Networks

View full text Add to dashboard Cite

Federated learning can effectively protect local data privacy in 5G-V2X environment and ensure data protection in Internet of vehicles environment. The advantages of low delay of 5G network should be better utilized in the vehicle-road cooperative system. But the existing asynchronous federated learning obtains a local model through different node training and completes the update of the global model through the central server. There are problems such as single point of failure, privacy leakage, and deviation of aggregation parameters. In response to the above problems, we proposed a 5G-V2X-oriented asynchronous federated learning privacy-preserving computing model (AFLPC). We used an adaptive differential privacy mechanism to reduce noise while protecting data privacy. A weight-based asynchronous federated learning aggregation update method is proposed to reasonably control the proportion of parameters submitted by users with different training speeds in the aggregation parameters and actively update the aggregation parameters of lagging users, so as to effectively reduce the negative impact on the model caused by the different speed of finding you. Experiments show that the proposed method can effectively ensure the credibility and privacy of asynchronous federated learning in 5G-V2X scenarios and at the same time improve the utility of the model.

show abstract

Section: Introductionmentioning

confidence: 99%

AFLPC: An Asynchronous Federated Learning Privacy-Preserving Computing Model Applied to 5G-V2X

Huang

et al. 2022

Security and Communication Networks

View full text Add to dashboard Cite

show abstract

“…Finally, we would like to suggest some of the possible scopes, shortly for researcher and practitioner as a brainstorming concept: reducing the reaction time and maximizing VM's resource allocation considering the QoS factor; improving the load stability in WSN using RCNN learning; SVM-PSO based community Forensics and RNN techniques for Intrusion Detection. Feature selection from natural algorithm Koroniotis et al [133] Quality of service NF PSO and DL Enhance NF Al hawaitat et al [134] WS PNS PSO Jamming attack Shi et al [135] Anomaly detection P ADAID 1 Presented unsupervised clustering Usman et al [96] VM allocation VR EFPA 2 Energy-oriented allocation Singh et al [103] VM migration VR HBGA 3 Energy reduction Naik et al [130] VM allocation VR Fruit fly Reduce host migration Meng & Pan [136] Optimization VR FFOA solve MKP 4 Mosa & Paton [126] VM placement VR GA Reduce response time & maximize resources utilization Duan et al [137] Information leakage P DL Protect server Festag & Spreckelsen [138] Data leakage P DL Detection of protected health information Chari et al [125] Quality of service IA DL Generate password via cognitive information Li et al [139] Signal processing IA GA Feature extraction via EEG signal Saini & Kansal [127] WSN ACS SI Reduce energy consumption and increase network life time Chen et al [140] Biometric identification IA CNN Proposed GSLT-CNN using human brain EEG Cao & Fang [141] Multilayer defense scenario ACS SI Found proficient IPSO elucidating extensive WTA problem Aliyu et al [124] Resource allocation ACS Ant colony Illustrated faster convergence optimize makespan time Poonia [142] VAN ACS SI Found significant difference in VANET routing protocol and Swarm based protocol Verma et al [ [129] Feature extraction ID GA Reduce features to classify network packet Tan et al [148] Real time network attack intrusion ID NN Able to detect in network precisely…”

Section: Discussionmentioning

confidence: 99%

Applications and Evaluations ofBio-InspiredApproaches in Cloud Security: A Review

et al. 2020

View full text Add to dashboard Cite

Cloud computing gained much popularity in the recent past due to its many internet-based services related to data, application, operating system, and eliminating the need for central hardware access. Many of the challenges associated with cloud computing can be specified as network load, security intrusion, authentication, biometric identification, and information leakage. Numerous algorithms have been proposed and evaluated to solve those challenges. Among those, bio-inspired algorithms such as Evolutionary, Swarm, Immune, and Neural algorithms are the most prominent ones which are developed based on nature's ecosystems. Bio-inspired algorithms' adaptability allows many researchers and practitioners to utilize them to solve many security-related cloud computing issues. This paper aims to explore previous research, recent studies, challenges, and scope for further analysis of cloud security. Therefore, this study provides an overview of bio-inspired algorithms application and evaluations, taking into account cloud security challenges,

show abstract

“…Given the concerns of protecting patient information, medical data are often the property of individual institutions, and there is a lack of data-sharing systems to link institutions. Fortunately, this obstacle is beginning to be overcome, with privacy-preserving distributed DL (DDL) and multicenter data-sharing agreements [137][138][139]. DDL provides a privacy-preserving solution to enable multiple parties to jointly learn via a deep model without explicitly sharing local datasets.…”

Section: Data Access and Medical Ethicsmentioning

confidence: 99%

Artificial intelligence for assisting cancer diagnosis and treatment in the era of precision medicine

Chen

Lin

et al. 2021

Cancer Communications

124

View full text Add to dashboard Cite

Over the past decade, artificial intelligence (AI) has contributed substantially to the resolution of various medical problems, including cancer. Deep learning (DL), a subfield of AI, is characterized by its ability to perform automated feature extraction and has great power in the assimilation and evaluation of large amounts of complicated data. On the basis of a large quantity of medical data and novel computational technologies, AI, especially DL, has been applied in various aspects of oncology research and has the potential to enhance cancer diagnosis and treatment. These applications range from early cancer detection, diagnosis, classification and grading, molecular characterization of tumors, prediction of patient outcomes and treatment responses, personalized treatment, automatic radiotherapy workflows, novel anti‐cancer drug discovery, and clinical trials. In this review, we introduced the general principle of AI, summarized major areas of its application for cancer diagnosis and treatment, and discussed its future directions and remaining challenges. As the adoption of AI in clinical use is increasing, we anticipate the arrival of AI‐powered cancer care.

show abstract

Privacy-Preserving distributed deep learning based on secret sharing

Cited by 40 publications

References 15 publications

AFLPC: An Asynchronous Federated Learning Privacy-Preserving Computing Model Applied to 5G-V2X

AFLPC: An Asynchronous Federated Learning Privacy-Preserving Computing Model Applied to 5G-V2X

Applications and Evaluations ofBio-InspiredApproaches in Cloud Security: A Review

Artificial intelligence for assisting cancer diagnosis and treatment in the era of precision medicine

Contact Info

Product

Resources

About