Poisoning attacks and countermeasures in intelligent networks: Status quo and prospects
Over the past years, the emergence of intelligent networks empowered by machine learning techniques has brought great facilitates to different aspects of human life. However, using machine learning in intelligent networks also presents potential security and privacy threats. A common practice is the...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2022-04-01
|
| Series: | Digital Communications and Networks |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S235286482100050X |
| _version_ | 1818127677598466048 |
|---|---|
| author | Chen Wang Jian Chen Yang Yang Xiaoqiang Ma Jiangchuan Liu |
| author_facet | Chen Wang Jian Chen Yang Yang Xiaoqiang Ma Jiangchuan Liu |
| author_sort | Chen Wang |
| collection | DOAJ |
| description | Over the past years, the emergence of intelligent networks empowered by machine learning techniques has brought great facilitates to different aspects of human life. However, using machine learning in intelligent networks also presents potential security and privacy threats. A common practice is the so-called poisoning attacks where malicious users inject fake training data with the aim of corrupting the learned model. In this survey, we comprehensively review existing poisoning attacks as well as the countermeasures in intelligent networks for the first time. We emphasize and compare the principles of the formal poisoning attacks employed in different categories of learning algorithms, and analyze the strengths and limitations of corresponding defense methods in a compact form. We also highlight some remaining challenges and future directions in the attack-defense confrontation to promote further research in this emerging yet promising area. |
| first_indexed | 2024-12-11T07:21:10Z |
| format | Article |
| id | doaj.art-8c5a4c44c6744124a81a313740bd5946 |
| institution | Directory Open Access Journal |
| issn | 2352-8648 |
| language | English |
| last_indexed | 2024-12-11T07:21:10Z |
| publishDate | 2022-04-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | Digital Communications and Networks |
| spelling | doaj.art-8c5a4c44c6744124a81a313740bd59462022-12-22T01:16:05ZengKeAi Communications Co., Ltd.Digital Communications and Networks2352-86482022-04-0182225234Poisoning attacks and countermeasures in intelligent networks: Status quo and prospectsChen Wang0Jian Chen1Yang Yang2Xiaoqiang Ma3Jiangchuan Liu4School of Computer Science and Information Engineering, Hubei University, Wuhan, China; School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, 430074, ChinaSchool of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, 430074, ChinaSchool of Computer Science and Information Engineering, Hubei University, Wuhan, China; Corresponding author.School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, 430074, ChinaSchool of Computing Science at Simon Fraser University, British Columbia, CanadaOver the past years, the emergence of intelligent networks empowered by machine learning techniques has brought great facilitates to different aspects of human life. However, using machine learning in intelligent networks also presents potential security and privacy threats. A common practice is the so-called poisoning attacks where malicious users inject fake training data with the aim of corrupting the learned model. In this survey, we comprehensively review existing poisoning attacks as well as the countermeasures in intelligent networks for the first time. We emphasize and compare the principles of the formal poisoning attacks employed in different categories of learning algorithms, and analyze the strengths and limitations of corresponding defense methods in a compact form. We also highlight some remaining challenges and future directions in the attack-defense confrontation to promote further research in this emerging yet promising area.http://www.sciencedirect.com/science/article/pii/S235286482100050XMachine learningPoisoning attackIntelligent networksSecurity threat |
| spellingShingle | Chen Wang Jian Chen Yang Yang Xiaoqiang Ma Jiangchuan Liu Poisoning attacks and countermeasures in intelligent networks: Status quo and prospects Digital Communications and Networks Machine learning Poisoning attack Intelligent networks Security threat |
| title | Poisoning attacks and countermeasures in intelligent networks: Status quo and prospects |
| title_full | Poisoning attacks and countermeasures in intelligent networks: Status quo and prospects |
| title_fullStr | Poisoning attacks and countermeasures in intelligent networks: Status quo and prospects |
| title_full_unstemmed | Poisoning attacks and countermeasures in intelligent networks: Status quo and prospects |
| title_short | Poisoning attacks and countermeasures in intelligent networks: Status quo and prospects |
| title_sort | poisoning attacks and countermeasures in intelligent networks status quo and prospects |
| topic | Machine learning Poisoning attack Intelligent networks Security threat |
| url | http://www.sciencedirect.com/science/article/pii/S235286482100050X |
| work_keys_str_mv | AT chenwang poisoningattacksandcountermeasuresinintelligentnetworksstatusquoandprospects AT jianchen poisoningattacksandcountermeasuresinintelligentnetworksstatusquoandprospects AT yangyang poisoningattacksandcountermeasuresinintelligentnetworksstatusquoandprospects AT xiaoqiangma poisoningattacksandcountermeasuresinintelligentnetworksstatusquoandprospects AT jiangchuanliu poisoningattacksandcountermeasuresinintelligentnetworksstatusquoandprospects |