Research on federated learning approach based on local differential privacy
As a type of collaborative machine learning framework, federated learning is capable of preserving private data from participants while training the data into useful models.Nevertheless, from a viewpoint of information theory, it is still vulnerable for a curious server to infer private information...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2022-10-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2022189/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841539982924185600 |
|---|---|
| author | Haiyan KANG Yuanrui JI |
| author_facet | Haiyan KANG Yuanrui JI |
| author_sort | Haiyan KANG |
| collection | DOAJ |
| description | As a type of collaborative machine learning framework, federated learning is capable of preserving private data from participants while training the data into useful models.Nevertheless, from a viewpoint of information theory, it is still vulnerable for a curious server to infer private information from the shared models uploaded by participants.To solve the inference attack problem in federated learning training, a local differential privacy federated learning (LDP-FL) approach was proposed.Firstly, to ensure the federated model training process was protected from inference attacks, a local differential privacy mechanism was designed for transmission of parameters in federated learning.Secondly, a performance loss constraint mechanism for federated learning was proposed and designed to reduce the performance loss of local differential privacy federated model by optimizing the constraint range of the loss function.Finally, the effectiveness of proposed LDP-FL approach was verified by comparative experiments on MNIST and Fashion MNIST datasets. |
| format | Article |
| id | doaj-art-9101716c644d4f71871c8e73cf0bad7c |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2022-10-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-9101716c644d4f71871c8e73cf0bad7c2025-01-14T06:30:03ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2022-10-01439410559396149Research on federated learning approach based on local differential privacyHaiyan KANGYuanrui JIAs a type of collaborative machine learning framework, federated learning is capable of preserving private data from participants while training the data into useful models.Nevertheless, from a viewpoint of information theory, it is still vulnerable for a curious server to infer private information from the shared models uploaded by participants.To solve the inference attack problem in federated learning training, a local differential privacy federated learning (LDP-FL) approach was proposed.Firstly, to ensure the federated model training process was protected from inference attacks, a local differential privacy mechanism was designed for transmission of parameters in federated learning.Secondly, a performance loss constraint mechanism for federated learning was proposed and designed to reduce the performance loss of local differential privacy federated model by optimizing the constraint range of the loss function.Finally, the effectiveness of proposed LDP-FL approach was verified by comparative experiments on MNIST and Fashion MNIST datasets.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2022189/differential privacyfederated learningdeep learning |
| spellingShingle | Haiyan KANG Yuanrui JI Research on federated learning approach based on local differential privacy Tongxin xuebao differential privacy federated learning deep learning |
| title | Research on federated learning approach based on local differential privacy |
| title_full | Research on federated learning approach based on local differential privacy |
| title_fullStr | Research on federated learning approach based on local differential privacy |
| title_full_unstemmed | Research on federated learning approach based on local differential privacy |
| title_short | Research on federated learning approach based on local differential privacy |
| title_sort | research on federated learning approach based on local differential privacy |
| topic | differential privacy federated learning deep learning |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2022189/ |
| work_keys_str_mv | AT haiyankang researchonfederatedlearningapproachbasedonlocaldifferentialprivacy AT yuanruiji researchonfederatedlearningapproachbasedonlocaldifferentialprivacy |