A survey of security threats in federated learning
Abstract Federated learning is a distributed machine learning paradigm that emerged as a solution to the need for privacy protection in artificial intelligence. Like traditional machine learning, federated learning is threatened by multiple attacks, such as backdoor attacks, Byzantine attacks, and a...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2025-01-01
|
| Series: | Complex & Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s40747-024-01664-0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823861501893541888 |
|---|---|
| author | Yunhao Feng Yanming Guo Yinjian Hou Yulun Wu Mingrui Lao Tianyuan Yu Gang Liu |
| author_facet | Yunhao Feng Yanming Guo Yinjian Hou Yulun Wu Mingrui Lao Tianyuan Yu Gang Liu |
| author_sort | Yunhao Feng |
| collection | DOAJ |
| description | Abstract Federated learning is a distributed machine learning paradigm that emerged as a solution to the need for privacy protection in artificial intelligence. Like traditional machine learning, federated learning is threatened by multiple attacks, such as backdoor attacks, Byzantine attacks, and adversarial attacks. The weaknesses are exacerbated by the inaccessibility of data in federated learning, which makes it more difficult to defend against these threats. This points to the need for further research into defensive approaches to make federated learning a real solution for distributed machine learning paradigm with securing data privacy. Our survey provides a taxonomy of these threats and defense methods, describing the general situation of this vulnerability in federated learning. We also sort out the relationship between these methods, their advantages and disadvantages, and discuss future research directions regarding the security issues of federated learning from multiple perspectives. |
| format | Article |
| id | doaj-art-c70132478068421b85fe05787dc843b2 |
| institution | Kabale University |
| issn | 2199-4536 2198-6053 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Springer |
| record_format | Article |
| series | Complex & Intelligent Systems |
| spelling | doaj-art-c70132478068421b85fe05787dc843b22025-02-09T13:01:17ZengSpringerComplex & Intelligent Systems2199-45362198-60532025-01-0111212610.1007/s40747-024-01664-0A survey of security threats in federated learningYunhao Feng0Yanming Guo1Yinjian Hou2Yulun Wu3Mingrui Lao4Tianyuan Yu5Gang Liu6National University of Defense TechnologyNational University of Defense TechnologyNational University of Defense TechnologyNational University of Defense TechnologyNational University of Defense TechnologyNational University of Defense TechnologyHunan Institute of Science and TechnologyAbstract Federated learning is a distributed machine learning paradigm that emerged as a solution to the need for privacy protection in artificial intelligence. Like traditional machine learning, federated learning is threatened by multiple attacks, such as backdoor attacks, Byzantine attacks, and adversarial attacks. The weaknesses are exacerbated by the inaccessibility of data in federated learning, which makes it more difficult to defend against these threats. This points to the need for further research into defensive approaches to make federated learning a real solution for distributed machine learning paradigm with securing data privacy. Our survey provides a taxonomy of these threats and defense methods, describing the general situation of this vulnerability in federated learning. We also sort out the relationship between these methods, their advantages and disadvantages, and discuss future research directions regarding the security issues of federated learning from multiple perspectives.https://doi.org/10.1007/s40747-024-01664-0Federated learningTrustworthy artificial intelligenceNon-IID dataRobust model |
| spellingShingle | Yunhao Feng Yanming Guo Yinjian Hou Yulun Wu Mingrui Lao Tianyuan Yu Gang Liu A survey of security threats in federated learning Complex & Intelligent Systems Federated learning Trustworthy artificial intelligence Non-IID data Robust model |
| title | A survey of security threats in federated learning |
| title_full | A survey of security threats in federated learning |
| title_fullStr | A survey of security threats in federated learning |
| title_full_unstemmed | A survey of security threats in federated learning |
| title_short | A survey of security threats in federated learning |
| title_sort | survey of security threats in federated learning |
| topic | Federated learning Trustworthy artificial intelligence Non-IID data Robust model |
| url | https://doi.org/10.1007/s40747-024-01664-0 |
| work_keys_str_mv | AT yunhaofeng asurveyofsecuritythreatsinfederatedlearning AT yanmingguo asurveyofsecuritythreatsinfederatedlearning AT yinjianhou asurveyofsecuritythreatsinfederatedlearning AT yulunwu asurveyofsecuritythreatsinfederatedlearning AT mingruilao asurveyofsecuritythreatsinfederatedlearning AT tianyuanyu asurveyofsecuritythreatsinfederatedlearning AT gangliu asurveyofsecuritythreatsinfederatedlearning AT yunhaofeng surveyofsecuritythreatsinfederatedlearning AT yanmingguo surveyofsecuritythreatsinfederatedlearning AT yinjianhou surveyofsecuritythreatsinfederatedlearning AT yulunwu surveyofsecuritythreatsinfederatedlearning AT mingruilao surveyofsecuritythreatsinfederatedlearning AT tianyuanyu surveyofsecuritythreatsinfederatedlearning AT gangliu surveyofsecuritythreatsinfederatedlearning |