Cargando…

A Differential Privacy Strategy Based on Local Features of Non-Gaussian Noise in Federated Learning

As an emerging artificial intelligence technology, federated learning plays a significant role in privacy preservation in machine learning, although its main objective is to prevent peers from peeping data. However, attackers from the outside can steal metadata in transit and through data reconstruc...

Descripción completa

Detalles Bibliográficos
Autores principales: Wang, Xinyi, Wang, Jincheng, Ma, Xue, Wen, Chenglin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9003035/
https://www.ncbi.nlm.nih.gov/pubmed/35408039
http://dx.doi.org/10.3390/s22072424
_version_ 1784686035070877696
author Wang, Xinyi
Wang, Jincheng
Ma, Xue
Wen, Chenglin
author_facet Wang, Xinyi
Wang, Jincheng
Ma, Xue
Wen, Chenglin
author_sort Wang, Xinyi
collection PubMed
description As an emerging artificial intelligence technology, federated learning plays a significant role in privacy preservation in machine learning, although its main objective is to prevent peers from peeping data. However, attackers from the outside can steal metadata in transit and through data reconstruction or other techniques to obtain the original data, which poses a great threat to the security of the federated learning system. In this paper, we propose a differential privacy strategy including encryption and decryption methods based on local features of non-Gaussian noise, which aggregates the noisy metadata through a sequential Kalman filter in federated learning scenarios to increase the reliability of the federated learning method. We name the local features of non-Gaussian noise as the non-Gaussian noise fragments. Compared with the traditional methods, the proposed method shows stronger security performance for two reasons. Firstly, non-Gaussian noise fragments contain more complex statistics, making them more difficult for attackers to identify. Secondly, in order to obtain accurate statistical features, attackers must aggregate all of the noise fragments, which is very difficult due to the increasing number of clients. We conduct experiments that demonstrate that the proposed method can greatly enhanced the system’s security.
format Online
Article
Text
id pubmed-9003035
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-90030352022-04-13 A Differential Privacy Strategy Based on Local Features of Non-Gaussian Noise in Federated Learning Wang, Xinyi Wang, Jincheng Ma, Xue Wen, Chenglin Sensors (Basel) Article As an emerging artificial intelligence technology, federated learning plays a significant role in privacy preservation in machine learning, although its main objective is to prevent peers from peeping data. However, attackers from the outside can steal metadata in transit and through data reconstruction or other techniques to obtain the original data, which poses a great threat to the security of the federated learning system. In this paper, we propose a differential privacy strategy including encryption and decryption methods based on local features of non-Gaussian noise, which aggregates the noisy metadata through a sequential Kalman filter in federated learning scenarios to increase the reliability of the federated learning method. We name the local features of non-Gaussian noise as the non-Gaussian noise fragments. Compared with the traditional methods, the proposed method shows stronger security performance for two reasons. Firstly, non-Gaussian noise fragments contain more complex statistics, making them more difficult for attackers to identify. Secondly, in order to obtain accurate statistical features, attackers must aggregate all of the noise fragments, which is very difficult due to the increasing number of clients. We conduct experiments that demonstrate that the proposed method can greatly enhanced the system’s security. MDPI 2022-03-22 /pmc/articles/PMC9003035/ /pubmed/35408039 http://dx.doi.org/10.3390/s22072424 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Wang, Xinyi
Wang, Jincheng
Ma, Xue
Wen, Chenglin
A Differential Privacy Strategy Based on Local Features of Non-Gaussian Noise in Federated Learning
title A Differential Privacy Strategy Based on Local Features of Non-Gaussian Noise in Federated Learning
title_full A Differential Privacy Strategy Based on Local Features of Non-Gaussian Noise in Federated Learning
title_fullStr A Differential Privacy Strategy Based on Local Features of Non-Gaussian Noise in Federated Learning
title_full_unstemmed A Differential Privacy Strategy Based on Local Features of Non-Gaussian Noise in Federated Learning
title_short A Differential Privacy Strategy Based on Local Features of Non-Gaussian Noise in Federated Learning
title_sort differential privacy strategy based on local features of non-gaussian noise in federated learning
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9003035/
https://www.ncbi.nlm.nih.gov/pubmed/35408039
http://dx.doi.org/10.3390/s22072424
work_keys_str_mv AT wangxinyi adifferentialprivacystrategybasedonlocalfeaturesofnongaussiannoiseinfederatedlearning
AT wangjincheng adifferentialprivacystrategybasedonlocalfeaturesofnongaussiannoiseinfederatedlearning
AT maxue adifferentialprivacystrategybasedonlocalfeaturesofnongaussiannoiseinfederatedlearning
AT wenchenglin adifferentialprivacystrategybasedonlocalfeaturesofnongaussiannoiseinfederatedlearning
AT wangxinyi differentialprivacystrategybasedonlocalfeaturesofnongaussiannoiseinfederatedlearning
AT wangjincheng differentialprivacystrategybasedonlocalfeaturesofnongaussiannoiseinfederatedlearning
AT maxue differentialprivacystrategybasedonlocalfeaturesofnongaussiannoiseinfederatedlearning
AT wenchenglin differentialprivacystrategybasedonlocalfeaturesofnongaussiannoiseinfederatedlearning