Privacy-Preserving Federated Learning Using Homomorphic Encryption
Federated learning (FL) is a machine learning technique that enables distributed devices to train a learning model collaboratively without sharing their local data. FL-based systems can achieve much stronger privacy preservation since the distributed devices deliver only local model parameters train...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/2/734 |
| _version_ | 1797496094885675008 |
|---|---|
| author | Jaehyoung Park Hyuk Lim |
| author_facet | Jaehyoung Park Hyuk Lim |
| author_sort | Jaehyoung Park |
| collection | DOAJ |
| description | Federated learning (FL) is a machine learning technique that enables distributed devices to train a learning model collaboratively without sharing their local data. FL-based systems can achieve much stronger privacy preservation since the distributed devices deliver only local model parameters trained with local data to a centralized server. However, there exists a possibility that a centralized server or attackers infer/extract sensitive private information using the structure and parameters of local learning models. We propose employing homomorphic encryption (HE) scheme that can directly perform arithmetic operations on ciphertexts without decryption to protect the model parameters. Using the HE scheme, the proposed privacy-preserving federated learning (PPFL) algorithm enables the centralized server to aggregate encrypted local model parameters without decryption. Furthermore, the proposed algorithm allows each node to use a different HE private key in the same FL-based system using a distributed cryptosystem. The performance analysis and evaluation of the proposed PPFL algorithm are conducted in various cloud computing-based FL service scenarios. |
| first_indexed | 2024-03-10T01:58:46Z |
| format | Article |
| id | doaj.art-4ee03b38b9874c8b8b112cdac3e75c10 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T01:58:46Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-4ee03b38b9874c8b8b112cdac3e75c102023-11-23T12:51:48ZengMDPI AGApplied Sciences2076-34172022-01-0112273410.3390/app12020734Privacy-Preserving Federated Learning Using Homomorphic EncryptionJaehyoung Park0Hyuk Lim1School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology (GIST), Gwangju 61005, KoreaAI Graduate School, Gwangju Institute of Science and Technology (GIST), Gwangju 61005, KoreaFederated learning (FL) is a machine learning technique that enables distributed devices to train a learning model collaboratively without sharing their local data. FL-based systems can achieve much stronger privacy preservation since the distributed devices deliver only local model parameters trained with local data to a centralized server. However, there exists a possibility that a centralized server or attackers infer/extract sensitive private information using the structure and parameters of local learning models. We propose employing homomorphic encryption (HE) scheme that can directly perform arithmetic operations on ciphertexts without decryption to protect the model parameters. Using the HE scheme, the proposed privacy-preserving federated learning (PPFL) algorithm enables the centralized server to aggregate encrypted local model parameters without decryption. Furthermore, the proposed algorithm allows each node to use a different HE private key in the same FL-based system using a distributed cryptosystem. The performance analysis and evaluation of the proposed PPFL algorithm are conducted in various cloud computing-based FL service scenarios.https://www.mdpi.com/2076-3417/12/2/734privacy preservinghomomorphic encryptionfederated learning |
| spellingShingle | Jaehyoung Park Hyuk Lim Privacy-Preserving Federated Learning Using Homomorphic Encryption Applied Sciences privacy preserving homomorphic encryption federated learning |
| title | Privacy-Preserving Federated Learning Using Homomorphic Encryption |
| title_full | Privacy-Preserving Federated Learning Using Homomorphic Encryption |
| title_fullStr | Privacy-Preserving Federated Learning Using Homomorphic Encryption |
| title_full_unstemmed | Privacy-Preserving Federated Learning Using Homomorphic Encryption |
| title_short | Privacy-Preserving Federated Learning Using Homomorphic Encryption |
| title_sort | privacy preserving federated learning using homomorphic encryption |
| topic | privacy preserving homomorphic encryption federated learning |
| url | https://www.mdpi.com/2076-3417/12/2/734 |
| work_keys_str_mv | AT jaehyoungpark privacypreservingfederatedlearningusinghomomorphicencryption AT hyuklim privacypreservingfederatedlearningusinghomomorphicencryption |