Survey on vertical federated learning: algorithm, privacy and security
Federated learning （FL） is a distributed machine learning technology that enables joint construction of machine learning models by transmitting intermediate results （e.g., model parameters, parameter gradients, embedding representation, etc.） applied to data distributed across various institutions.F...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
POSTS&TELECOM PRESS Co., LTD
2023-04-01
|
| Series: | 网络与信息安全学报 |
| Subjects: | |
| Online Access: | https://www.infocomm-journal.com/cjnis/CN/10.11959/j.issn.2096-109x.2023017 |
| _version_ | 1797262527570116608 |
|---|---|
| author | Jinyin CHEN, Rongchang LI, Guohan HUANG, Tao LIU, Haibin ZHENG, Yao CHENG |
| author_facet | Jinyin CHEN, Rongchang LI, Guohan HUANG, Tao LIU, Haibin ZHENG, Yao CHENG |
| author_sort | Jinyin CHEN, Rongchang LI, Guohan HUANG, Tao LIU, Haibin ZHENG, Yao CHENG |
| collection | DOAJ |
| description | Federated learning （FL） is a distributed machine learning technology that enables joint construction of machine learning models by transmitting intermediate results （e.g., model parameters, parameter gradients, embedding representation, etc.） applied to data distributed across various institutions.FL reduces the risk of privacy leakage, since raw data is not allowed to leave the institution.According to the difference in data distribution between institutions, FL is usually divided into horizontal federated learning （HFL）, vertical federated learning （VFL）, and federal transfer learning （TFL）.VFL is suitable for scenarios where institutions have the same sample space but different feature spaces and is widely used in fields such as medical diagnosis, financial and security of VFL.Although VFL performs well in real-world applications, it still faces many privacy and security challenges.To the best of our knowledge, no comprehensive survey has been conducted on privacy and security methods.The existing VFL was analyzed from four perspectives: the basic framework, communication mechanism, alignment mechanism, and label processing mechanism.Then the privacy and security risks faced by VFL and the related defense methods were introduced and analyzed.Additionally, the common data sets and indicators suitable for VFL and platform framework were presented.Considering the existing challenges and problems, the future direction and development trend of VFL were outlined, to provide a reference for the theoretical research of building an efficient, robust and safe VFL. |
| first_indexed | 2024-04-24T23:58:32Z |
| format | Article |
| id | doaj.art-9ce57f0975564ac4b10528388f45c624 |
| institution | Directory Open Access Journal |
| issn | 2096-109X |
| language | English |
| last_indexed | 2024-04-24T23:58:32Z |
| publishDate | 2023-04-01 |
| publisher | POSTS&TELECOM PRESS Co., LTD |
| record_format | Article |
| series | 网络与信息安全学报 |
| spelling | doaj.art-9ce57f0975564ac4b10528388f45c6242024-03-14T09:49:23ZengPOSTS&TELECOM PRESS Co., LTD网络与信息安全学报2096-109X2023-04-019212010.11959/j.issn.2096-109x.2023017Survey on vertical federated learning: algorithm, privacy and securityJinyin CHEN, Rongchang LI, Guohan HUANG, Tao LIU, Haibin ZHENG, Yao CHENGFederated learning （FL） is a distributed machine learning technology that enables joint construction of machine learning models by transmitting intermediate results （e.g., model parameters, parameter gradients, embedding representation, etc.） applied to data distributed across various institutions.FL reduces the risk of privacy leakage, since raw data is not allowed to leave the institution.According to the difference in data distribution between institutions, FL is usually divided into horizontal federated learning （HFL）, vertical federated learning （VFL）, and federal transfer learning （TFL）.VFL is suitable for scenarios where institutions have the same sample space but different feature spaces and is widely used in fields such as medical diagnosis, financial and security of VFL.Although VFL performs well in real-world applications, it still faces many privacy and security challenges.To the best of our knowledge, no comprehensive survey has been conducted on privacy and security methods.The existing VFL was analyzed from four perspectives: the basic framework, communication mechanism, alignment mechanism, and label processing mechanism.Then the privacy and security risks faced by VFL and the related defense methods were introduced and analyzed.Additionally, the common data sets and indicators suitable for VFL and platform framework were presented.Considering the existing challenges and problems, the future direction and development trend of VFL were outlined, to provide a reference for the theoretical research of building an efficient, robust and safe VFL.https://www.infocomm-journal.com/cjnis/CN/10.11959/j.issn.2096-109x.2023017vertical federated learningsecurity and privacybackdoor attackinference attack and defenseadversarial attacksecurity evaluation |
| spellingShingle | Jinyin CHEN, Rongchang LI, Guohan HUANG, Tao LIU, Haibin ZHENG, Yao CHENG Survey on vertical federated learning: algorithm, privacy and security 网络与信息安全学报 vertical federated learning security and privacy backdoor attack inference attack and defense adversarial attack security evaluation |
| title | Survey on vertical federated learning: algorithm, privacy and security |
| title_full | Survey on vertical federated learning: algorithm, privacy and security |
| title_fullStr | Survey on vertical federated learning: algorithm, privacy and security |
| title_full_unstemmed | Survey on vertical federated learning: algorithm, privacy and security |
| title_short | Survey on vertical federated learning: algorithm, privacy and security |
| title_sort | survey on vertical federated learning algorithm privacy and security |
| topic | vertical federated learning security and privacy backdoor attack inference attack and defense adversarial attack security evaluation |
| url | https://www.infocomm-journal.com/cjnis/CN/10.11959/j.issn.2096-109x.2023017 |
| work_keys_str_mv | AT jinyinchenrongchangliguohanhuangtaoliuhaibinzhengyaocheng surveyonverticalfederatedlearningalgorithmprivacyandsecurity |