Privacy-Preserving Federated Learning via Homomorphic Adversarial Networks
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916936506408960 |
|---|---|
| author | Dong, Wenhan Lin, Chao He, Xinlei Xu, Shengmin Huang, Xinyi |
| author_facet | Dong, Wenhan Lin, Chao He, Xinlei Xu, Shengmin Huang, Xinyi |
| contents | Privacy-preserving federated learning (PPFL) aims to train a global model for multiple clients while maintaining their data privacy. However, current PPFL protocols exhibit one or more of the following insufficiencies: considerable degradation in accuracy, the requirement for sharing keys, and cooperation during the key generation or decryption processes. As a mitigation, we develop the first protocol that utilizes neural networks to implement PPFL, as well as incorporating an Aggregatable Hybrid Encryption scheme tailored to the needs of PPFL. We name these networks as Homomorphic Adversarial Networks (HANs) which demonstrate that neural networks are capable of performing tasks similar to multi-key homomorphic encryption (MK-HE) while solving the problems of key distribution and collaborative decryption. Our experiments show that HANs are robust against privacy attacks. Compared with non-private federated learning, experiments conducted on multiple datasets demonstrate that HANs exhibit a negligible accuracy loss (at most 1.35%). Compared to traditional MK-HE schemes, HANs increase encryption aggregation speed by 6,075 times while incurring a 29.2 times increase in communication overhead. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_01650 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Privacy-Preserving Federated Learning via Homomorphic Adversarial Networks Dong, Wenhan Lin, Chao He, Xinlei Xu, Shengmin Huang, Xinyi Cryptography and Security Artificial Intelligence Machine Learning Privacy-preserving federated learning (PPFL) aims to train a global model for multiple clients while maintaining their data privacy. However, current PPFL protocols exhibit one or more of the following insufficiencies: considerable degradation in accuracy, the requirement for sharing keys, and cooperation during the key generation or decryption processes. As a mitigation, we develop the first protocol that utilizes neural networks to implement PPFL, as well as incorporating an Aggregatable Hybrid Encryption scheme tailored to the needs of PPFL. We name these networks as Homomorphic Adversarial Networks (HANs) which demonstrate that neural networks are capable of performing tasks similar to multi-key homomorphic encryption (MK-HE) while solving the problems of key distribution and collaborative decryption. Our experiments show that HANs are robust against privacy attacks. Compared with non-private federated learning, experiments conducted on multiple datasets demonstrate that HANs exhibit a negligible accuracy loss (at most 1.35%). Compared to traditional MK-HE schemes, HANs increase encryption aggregation speed by 6,075 times while incurring a 29.2 times increase in communication overhead. |
| title | Privacy-Preserving Federated Learning via Homomorphic Adversarial Networks |
| topic | Cryptography and Security Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2412.01650 |