Efficient Byzantine-Robust and Provably Privacy-Preserving Federated Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913450309976064 |
|---|---|
| author | Nie, Chenfei Li, Qiang Yang, Yuxin Ji, Yuede Wang, Binghui |
| author_facet | Nie, Chenfei Li, Qiang Yang, Yuxin Ji, Yuede Wang, Binghui |
| contents | Federated learning (FL) is an emerging distributed learning paradigm without sharing participating clients' private data. However, existing works show that FL is vulnerable to both Byzantine (security) attacks and data reconstruction (privacy) attacks. Almost all the existing FL defenses only address one of the two attacks. A few defenses address the two attacks, but they are not efficient and effective enough. We propose BPFL, an efficient Byzantine-robust and provably privacy-preserving FL method that addresses all the issues. Specifically, we draw on state-of-the-art Byzantine-robust FL methods and use similarity metrics to measure the robustness of each participating client in FL. The validity of clients are formulated as circuit constraints on similarity metrics and verified via a zero-knowledge proof. Moreover, the client models are masked by a shared random vector, which is generated based on homomorphic encryption. In doing so, the server receives the masked client models rather than the true ones, which are proven to be private. BPFL is also efficient due to the usage of non-interactive zero-knowledge proof. Experimental results on various datasets show that our BPFL is efficient, Byzantine-robust, and privacy-preserving. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_19703 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Efficient Byzantine-Robust and Provably Privacy-Preserving Federated Learning Nie, Chenfei Li, Qiang Yang, Yuxin Ji, Yuede Wang, Binghui Cryptography and Security Federated learning (FL) is an emerging distributed learning paradigm without sharing participating clients' private data. However, existing works show that FL is vulnerable to both Byzantine (security) attacks and data reconstruction (privacy) attacks. Almost all the existing FL defenses only address one of the two attacks. A few defenses address the two attacks, but they are not efficient and effective enough. We propose BPFL, an efficient Byzantine-robust and provably privacy-preserving FL method that addresses all the issues. Specifically, we draw on state-of-the-art Byzantine-robust FL methods and use similarity metrics to measure the robustness of each participating client in FL. The validity of clients are formulated as circuit constraints on similarity metrics and verified via a zero-knowledge proof. Moreover, the client models are masked by a shared random vector, which is generated based on homomorphic encryption. In doing so, the server receives the masked client models rather than the true ones, which are proven to be private. BPFL is also efficient due to the usage of non-interactive zero-knowledge proof. Experimental results on various datasets show that our BPFL is efficient, Byzantine-robust, and privacy-preserving. |
| title | Efficient Byzantine-Robust and Provably Privacy-Preserving Federated Learning |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2407.19703 |