Survey on model inversion attack and defense in federated learning
As a distributed machine learning technology, federated learning can solve the problem of data islands.However, because machine learning models will unconsciously remember training data, model parameters and global models uploaded by participants will suffer various privacy attacks.A systematic summ...
Saved in:
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | zho |
Published: |
Editorial Department of Journal on Communications
2023-11-01
|
Series: | Tongxin xuebao |
Subjects: | |
Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2023209/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
_version_ | 1841540064020004864 |
---|---|
author | Dong WANG Qianqian QIN Kaitian GUO Rongke LIU Weipeng YAN Yizhi REN Qingcai LUO Yanzhao SHEN |
author_facet | Dong WANG Qianqian QIN Kaitian GUO Rongke LIU Weipeng YAN Yizhi REN Qingcai LUO Yanzhao SHEN |
author_sort | Dong WANG |
collection | DOAJ |
description | As a distributed machine learning technology, federated learning can solve the problem of data islands.However, because machine learning models will unconsciously remember training data, model parameters and global models uploaded by participants will suffer various privacy attacks.A systematic summary of existing attack methods was conducted for model inversion attacks in privacy attacks.Firstly, the theoretical framework of model inversion attack was summarized and analyzed in detail.Then, existing attack methods from the perspective of threat models were summarized, analyzed and compared.Then, the defense strategies of different technology types were summarized and compared.Finally, the commonly used evaluation criteria and datasets were summarized for inversion attack of existing models, and the main challenges and future research directions were summarized for inversion attack of models. |
format | Article |
id | doaj-art-ad1beedf3d7243f397a5156476b792be |
institution | Kabale University |
issn | 1000-436X |
language | zho |
publishDate | 2023-11-01 |
publisher | Editorial Department of Journal on Communications |
record_format | Article |
series | Tongxin xuebao |
spelling | doaj-art-ad1beedf3d7243f397a5156476b792be2025-01-14T06:28:13ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2023-11-01449410959389501Survey on model inversion attack and defense in federated learningDong WANGQianqian QINKaitian GUORongke LIUWeipeng YANYizhi RENQingcai LUOYanzhao SHENAs a distributed machine learning technology, federated learning can solve the problem of data islands.However, because machine learning models will unconsciously remember training data, model parameters and global models uploaded by participants will suffer various privacy attacks.A systematic summary of existing attack methods was conducted for model inversion attacks in privacy attacks.Firstly, the theoretical framework of model inversion attack was summarized and analyzed in detail.Then, existing attack methods from the perspective of threat models were summarized, analyzed and compared.Then, the defense strategies of different technology types were summarized and compared.Finally, the commonly used evaluation criteria and datasets were summarized for inversion attack of existing models, and the main challenges and future research directions were summarized for inversion attack of models.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2023209/federated learningmodel inversion attackprivacy security |
spellingShingle | Dong WANG Qianqian QIN Kaitian GUO Rongke LIU Weipeng YAN Yizhi REN Qingcai LUO Yanzhao SHEN Survey on model inversion attack and defense in federated learning Tongxin xuebao federated learning model inversion attack privacy security |
title | Survey on model inversion attack and defense in federated learning |
title_full | Survey on model inversion attack and defense in federated learning |
title_fullStr | Survey on model inversion attack and defense in federated learning |
title_full_unstemmed | Survey on model inversion attack and defense in federated learning |
title_short | Survey on model inversion attack and defense in federated learning |
title_sort | survey on model inversion attack and defense in federated learning |
topic | federated learning model inversion attack privacy security |
url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2023209/ |
work_keys_str_mv | AT dongwang surveyonmodelinversionattackanddefenseinfederatedlearning AT qianqianqin surveyonmodelinversionattackanddefenseinfederatedlearning AT kaitianguo surveyonmodelinversionattackanddefenseinfederatedlearning AT rongkeliu surveyonmodelinversionattackanddefenseinfederatedlearning AT weipengyan surveyonmodelinversionattackanddefenseinfederatedlearning AT yizhiren surveyonmodelinversionattackanddefenseinfederatedlearning AT qingcailuo surveyonmodelinversionattackanddefenseinfederatedlearning AT yanzhaoshen surveyonmodelinversionattackanddefenseinfederatedlearning |