FedAdOb: Privacy-Preserving Federated Deep Learning with Adaptive Obfuscation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910469351014400 |
|---|---|
| author | Gu, Hanlin Luo, Jiahuan Kang, Yan Yao, Yuan Zhu, Gongxi Li, Bowen Fan, Lixin Yang, Qiang |
| author_facet | Gu, Hanlin Luo, Jiahuan Kang, Yan Yao, Yuan Zhu, Gongxi Li, Bowen Fan, Lixin Yang, Qiang |
| contents | Federated learning (FL) has emerged as a collaborative approach that allows multiple clients to jointly learn a machine learning model without sharing their private data. The concern about privacy leakage, albeit demonstrated under specific conditions, has triggered numerous follow-up research in designing powerful attacking methods and effective defending mechanisms aiming to thwart these attacking methods. Nevertheless, privacy-preserving mechanisms employed in these defending methods invariably lead to compromised model performances due to a fixed obfuscation applied to private data or gradients. In this article, we, therefore, propose a novel adaptive obfuscation mechanism, coined FedAdOb, to protect private data without yielding original model performances. Technically, FedAdOb utilizes passport-based adaptive obfuscation to ensure data privacy in both horizontal and vertical federated learning settings. The privacy-preserving capabilities of FedAdOb, specifically with regard to private features and labels, are theoretically proven through Theorems 1 and 2. Furthermore, extensive experimental evaluations conducted on various datasets and network architectures demonstrate the effectiveness of FedAdOb by manifesting its superior trade-off between privacy preservation and model performance, surpassing existing methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_01085 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FedAdOb: Privacy-Preserving Federated Deep Learning with Adaptive Obfuscation Gu, Hanlin Luo, Jiahuan Kang, Yan Yao, Yuan Zhu, Gongxi Li, Bowen Fan, Lixin Yang, Qiang Cryptography and Security Artificial Intelligence Federated learning (FL) has emerged as a collaborative approach that allows multiple clients to jointly learn a machine learning model without sharing their private data. The concern about privacy leakage, albeit demonstrated under specific conditions, has triggered numerous follow-up research in designing powerful attacking methods and effective defending mechanisms aiming to thwart these attacking methods. Nevertheless, privacy-preserving mechanisms employed in these defending methods invariably lead to compromised model performances due to a fixed obfuscation applied to private data or gradients. In this article, we, therefore, propose a novel adaptive obfuscation mechanism, coined FedAdOb, to protect private data without yielding original model performances. Technically, FedAdOb utilizes passport-based adaptive obfuscation to ensure data privacy in both horizontal and vertical federated learning settings. The privacy-preserving capabilities of FedAdOb, specifically with regard to private features and labels, are theoretically proven through Theorems 1 and 2. Furthermore, extensive experimental evaluations conducted on various datasets and network architectures demonstrate the effectiveness of FedAdOb by manifesting its superior trade-off between privacy preservation and model performance, surpassing existing methods. |
| title | FedAdOb: Privacy-Preserving Federated Deep Learning with Adaptive Obfuscation |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2406.01085 |