Efficient secure federated learning aggregation framework based on homomorphic encryption
In order to solve the problems of data security and communication overhead in federated learning, an efficient and secure federated aggregation framework based on homomorphic encryption was proposed.In the process of federated learning, the privacy and security issues of user data need to be solved...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2023-01-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2023015/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841540071421902848 |
|---|---|
| author | Shengxing YU Zhong CHEN |
| author_facet | Shengxing YU Zhong CHEN |
| author_sort | Shengxing YU |
| collection | DOAJ |
| description | In order to solve the problems of data security and communication overhead in federated learning, an efficient and secure federated aggregation framework based on homomorphic encryption was proposed.In the process of federated learning, the privacy and security issues of user data need to be solved urgently.However, the computational cost and communication overhead caused by the encryption scheme would affect the training efficiency.Firstly, in the case of protecting data security and ensuring training efficiency, the Top-K gradient selection method was used to screen model gradients, reducing the number of gradients that need to be uploaded.A candidate quantization protocol suitable for multi-edge terminals and a secure candidate index merging algorithm were proposed to further reduce communication overhead and accelerate homomorphic encryption calculations.Secondly, since model parameters of each layer of neural networks had characteristics of the Gaussian distribution, the selected model gradients were clipped and quantized, and the gradient unsigned quantization protocol was adopted to speed up the homomorphic encryption calculation.Finally, the experimental results show that in the federated learning scenario, the proposed framework can protect data privacy, and has high accuracy and efficient performance. |
| format | Article |
| id | doaj-art-c87099cf2dcf441991de77b45c04331c |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2023-01-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-c87099cf2dcf441991de77b45c04331c2025-01-14T06:23:38ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2023-01-0144142859388742Efficient secure federated learning aggregation framework based on homomorphic encryptionShengxing YUZhong CHENIn order to solve the problems of data security and communication overhead in federated learning, an efficient and secure federated aggregation framework based on homomorphic encryption was proposed.In the process of federated learning, the privacy and security issues of user data need to be solved urgently.However, the computational cost and communication overhead caused by the encryption scheme would affect the training efficiency.Firstly, in the case of protecting data security and ensuring training efficiency, the Top-K gradient selection method was used to screen model gradients, reducing the number of gradients that need to be uploaded.A candidate quantization protocol suitable for multi-edge terminals and a secure candidate index merging algorithm were proposed to further reduce communication overhead and accelerate homomorphic encryption calculations.Secondly, since model parameters of each layer of neural networks had characteristics of the Gaussian distribution, the selected model gradients were clipped and quantized, and the gradient unsigned quantization protocol was adopted to speed up the homomorphic encryption calculation.Finally, the experimental results show that in the federated learning scenario, the proposed framework can protect data privacy, and has high accuracy and efficient performance.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2023015/federated learninghomomorphic encryptionprivacy-preservingquantization protocol |
| spellingShingle | Shengxing YU Zhong CHEN Efficient secure federated learning aggregation framework based on homomorphic encryption Tongxin xuebao federated learning homomorphic encryption privacy-preserving quantization protocol |
| title | Efficient secure federated learning aggregation framework based on homomorphic encryption |
| title_full | Efficient secure federated learning aggregation framework based on homomorphic encryption |
| title_fullStr | Efficient secure federated learning aggregation framework based on homomorphic encryption |
| title_full_unstemmed | Efficient secure federated learning aggregation framework based on homomorphic encryption |
| title_short | Efficient secure federated learning aggregation framework based on homomorphic encryption |
| title_sort | efficient secure federated learning aggregation framework based on homomorphic encryption |
| topic | federated learning homomorphic encryption privacy-preserving quantization protocol |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2023015/ |
| work_keys_str_mv | AT shengxingyu efficientsecurefederatedlearningaggregationframeworkbasedonhomomorphicencryption AT zhongchen efficientsecurefederatedlearningaggregationframeworkbasedonhomomorphicencryption |