WW-FL: Secure and Private Large-Scale Federated Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918159717498880 |
|---|---|
| author | Marx, Felix Schneider, Thomas Suresh, Ajith Wehrle, Tobias Weinert, Christian Yalame, Hossein |
| author_facet | Marx, Felix Schneider, Thomas Suresh, Ajith Wehrle, Tobias Weinert, Christian Yalame, Hossein |
| contents | Federated learning (FL) is an efficient approach for large-scale distributed machine learning that promises data privacy by keeping training data on client devices. However, recent research has uncovered vulnerabilities in FL, impacting both security and privacy through poisoning attacks and the potential disclosure of sensitive information in individual model updates as well as the aggregated global model. This paper explores the inadequacies of existing FL protection measures when applied independently, and the challenges of creating effective compositions.
Addressing these issues, we propose WW-FL, an innovative framework that combines secure multi-party computation (MPC) with hierarchical FL to guarantee data and global model privacy. One notable feature of WW-FL is its capability to prevent malicious clients from directly poisoning model parameters, confining them to less destructive data poisoning attacks. We furthermore provide a PyTorch-based FL implementation integrated with Meta's CrypTen MPC framework to systematically measure the performance and robustness of WW-FL. Our extensive evaluation demonstrates that WW-FL is a promising solution for secure and private large-scale federated learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2302_09904 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | WW-FL: Secure and Private Large-Scale Federated Learning Marx, Felix Schneider, Thomas Suresh, Ajith Wehrle, Tobias Weinert, Christian Yalame, Hossein Machine Learning Cryptography and Security Distributed, Parallel, and Cluster Computing Information Theory Federated learning (FL) is an efficient approach for large-scale distributed machine learning that promises data privacy by keeping training data on client devices. However, recent research has uncovered vulnerabilities in FL, impacting both security and privacy through poisoning attacks and the potential disclosure of sensitive information in individual model updates as well as the aggregated global model. This paper explores the inadequacies of existing FL protection measures when applied independently, and the challenges of creating effective compositions. Addressing these issues, we propose WW-FL, an innovative framework that combines secure multi-party computation (MPC) with hierarchical FL to guarantee data and global model privacy. One notable feature of WW-FL is its capability to prevent malicious clients from directly poisoning model parameters, confining them to less destructive data poisoning attacks. We furthermore provide a PyTorch-based FL implementation integrated with Meta's CrypTen MPC framework to systematically measure the performance and robustness of WW-FL. Our extensive evaluation demonstrates that WW-FL is a promising solution for secure and private large-scale federated learning. |
| title | WW-FL: Secure and Private Large-Scale Federated Learning |
| topic | Machine Learning Cryptography and Security Distributed, Parallel, and Cluster Computing Information Theory |
| url | https://arxiv.org/abs/2302.09904 |