A Differential Privacy Strategy Based on Local Features of Non-Gaussian Noise in Federated Learning
As an emerging artificial intelligence technology, federated learning plays a significant role in privacy preservation in machine learning, although its main objective is to prevent peers from peeping data. However, attackers from the outside can steal metadata in transit and through data reconstruc...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/7/2424 |
| _version_ | 1797437760652443648 |
|---|---|
| author | Xinyi Wang Jincheng Wang Xue Ma Chenglin Wen |
| author_facet | Xinyi Wang Jincheng Wang Xue Ma Chenglin Wen |
| author_sort | Xinyi Wang |
| collection | DOAJ |
| description | As an emerging artificial intelligence technology, federated learning plays a significant role in privacy preservation in machine learning, although its main objective is to prevent peers from peeping data. However, attackers from the outside can steal metadata in transit and through data reconstruction or other techniques to obtain the original data, which poses a great threat to the security of the federated learning system. In this paper, we propose a differential privacy strategy including encryption and decryption methods based on local features of non-Gaussian noise, which aggregates the noisy metadata through a sequential Kalman filter in federated learning scenarios to increase the reliability of the federated learning method. We name the local features of non-Gaussian noise as the non-Gaussian noise fragments. Compared with the traditional methods, the proposed method shows stronger security performance for two reasons. Firstly, non-Gaussian noise fragments contain more complex statistics, making them more difficult for attackers to identify. Secondly, in order to obtain accurate statistical features, attackers must aggregate all of the noise fragments, which is very difficult due to the increasing number of clients. We conduct experiments that demonstrate that the proposed method can greatly enhanced the system’s security. |
| first_indexed | 2024-03-09T11:27:15Z |
| format | Article |
| id | doaj.art-26847d62c203438a81433a99aa938695 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T11:27:15Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-26847d62c203438a81433a99aa9386952023-11-30T23:58:43ZengMDPI AGSensors1424-82202022-03-01227242410.3390/s22072424A Differential Privacy Strategy Based on Local Features of Non-Gaussian Noise in Federated LearningXinyi Wang0Jincheng Wang1Xue Ma2Chenglin Wen3School of Automation, Hangzhou Dianzi University, Hangzhou 310018, ChinaSchool of Automation, Hangzhou Dianzi University, Hangzhou 310018, ChinaSchool of Automation, Hangzhou Dianzi University, Hangzhou 310018, ChinaSchool of Automation, Guangdong University of Petrochemical Technology, Maoming 525000, ChinaAs an emerging artificial intelligence technology, federated learning plays a significant role in privacy preservation in machine learning, although its main objective is to prevent peers from peeping data. However, attackers from the outside can steal metadata in transit and through data reconstruction or other techniques to obtain the original data, which poses a great threat to the security of the federated learning system. In this paper, we propose a differential privacy strategy including encryption and decryption methods based on local features of non-Gaussian noise, which aggregates the noisy metadata through a sequential Kalman filter in federated learning scenarios to increase the reliability of the federated learning method. We name the local features of non-Gaussian noise as the non-Gaussian noise fragments. Compared with the traditional methods, the proposed method shows stronger security performance for two reasons. Firstly, non-Gaussian noise fragments contain more complex statistics, making them more difficult for attackers to identify. Secondly, in order to obtain accurate statistical features, attackers must aggregate all of the noise fragments, which is very difficult due to the increasing number of clients. We conduct experiments that demonstrate that the proposed method can greatly enhanced the system’s security.https://www.mdpi.com/1424-8220/22/7/2424federated learning (FL)differential privacyKalman filternon-Gaussian noise |
| spellingShingle | Xinyi Wang Jincheng Wang Xue Ma Chenglin Wen A Differential Privacy Strategy Based on Local Features of Non-Gaussian Noise in Federated Learning Sensors federated learning (FL) differential privacy Kalman filter non-Gaussian noise |
| title | A Differential Privacy Strategy Based on Local Features of Non-Gaussian Noise in Federated Learning |
| title_full | A Differential Privacy Strategy Based on Local Features of Non-Gaussian Noise in Federated Learning |
| title_fullStr | A Differential Privacy Strategy Based on Local Features of Non-Gaussian Noise in Federated Learning |
| title_full_unstemmed | A Differential Privacy Strategy Based on Local Features of Non-Gaussian Noise in Federated Learning |
| title_short | A Differential Privacy Strategy Based on Local Features of Non-Gaussian Noise in Federated Learning |
| title_sort | differential privacy strategy based on local features of non gaussian noise in federated learning |
| topic | federated learning (FL) differential privacy Kalman filter non-Gaussian noise |
| url | https://www.mdpi.com/1424-8220/22/7/2424 |
| work_keys_str_mv | AT xinyiwang adifferentialprivacystrategybasedonlocalfeaturesofnongaussiannoiseinfederatedlearning AT jinchengwang adifferentialprivacystrategybasedonlocalfeaturesofnongaussiannoiseinfederatedlearning AT xuema adifferentialprivacystrategybasedonlocalfeaturesofnongaussiannoiseinfederatedlearning AT chenglinwen adifferentialprivacystrategybasedonlocalfeaturesofnongaussiannoiseinfederatedlearning AT xinyiwang differentialprivacystrategybasedonlocalfeaturesofnongaussiannoiseinfederatedlearning AT jinchengwang differentialprivacystrategybasedonlocalfeaturesofnongaussiannoiseinfederatedlearning AT xuema differentialprivacystrategybasedonlocalfeaturesofnongaussiannoiseinfederatedlearning AT chenglinwen differentialprivacystrategybasedonlocalfeaturesofnongaussiannoiseinfederatedlearning |