Byzantine-Resilient Secure Aggregation for Federated Learning Without Privacy Compromises
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_ | 1866912427097980928 |
|---|---|
| author | Xia, Yue Hofmeister, Christoph Egger, Maximilian Bitar, Rawad |
| author_facet | Xia, Yue Hofmeister, Christoph Egger, Maximilian Bitar, Rawad |
| contents | Federated learning (FL) shows great promise in large scale machine learning, but brings new risks in terms of privacy and security. We propose ByITFL, a novel scheme for FL that provides resilience against Byzantine users while keeping the users' data private from the federator and private from other users. The scheme builds on the preexisting non-private FLTrust scheme, which tolerates malicious users through trust scores (TS) that attenuate or amplify the users' gradients. The trust scores are based on the ReLU function, which we approximate by a polynomial. The distributed and privacy-preserving computation in ByITFL is designed using a combination of Lagrange coded computing, verifiable secret sharing and re-randomization steps. ByITFL is the first Byzantine resilient scheme for FL with full information-theoretic privacy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_08698 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Byzantine-Resilient Secure Aggregation for Federated Learning Without Privacy Compromises Xia, Yue Hofmeister, Christoph Egger, Maximilian Bitar, Rawad Information Theory Cryptography and Security Distributed, Parallel, and Cluster Computing Machine Learning Federated learning (FL) shows great promise in large scale machine learning, but brings new risks in terms of privacy and security. We propose ByITFL, a novel scheme for FL that provides resilience against Byzantine users while keeping the users' data private from the federator and private from other users. The scheme builds on the preexisting non-private FLTrust scheme, which tolerates malicious users through trust scores (TS) that attenuate or amplify the users' gradients. The trust scores are based on the ReLU function, which we approximate by a polynomial. The distributed and privacy-preserving computation in ByITFL is designed using a combination of Lagrange coded computing, verifiable secret sharing and re-randomization steps. ByITFL is the first Byzantine resilient scheme for FL with full information-theoretic privacy. |
| title | Byzantine-Resilient Secure Aggregation for Federated Learning Without Privacy Compromises |
| topic | Information Theory Cryptography and Security Distributed, Parallel, and Cluster Computing Machine Learning |
| url | https://arxiv.org/abs/2405.08698 |