Blockchain-enabled Trustworthy Federated Unlearning
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_ | 1866914656403062784 |
|---|---|
| author | Lin, Yijing Gao, Zhipeng Du, Hongyang Ren, Jinke Xie, Zhiqiang Niyato, Dusit |
| author_facet | Lin, Yijing Gao, Zhipeng Du, Hongyang Ren, Jinke Xie, Zhiqiang Niyato, Dusit |
| contents | Federated unlearning is a promising paradigm for protecting the data ownership of distributed clients. It allows central servers to remove historical data effects within the machine learning model as well as address the "right to be forgotten" issue in federated learning. However, existing works require central servers to retain the historical model parameters from distributed clients, such that allows the central server to utilize these parameters for further training even, after the clients exit the training process. To address this issue, this paper proposes a new blockchain-enabled trustworthy federated unlearning framework. We first design a proof of federated unlearning protocol, which utilizes the Chameleon hash function to verify data removal and eliminate the data contributions stored in other clients' models. Then, an adaptive contribution-based retraining mechanism is developed to reduce the computational overhead and significantly improve the training efficiency. Extensive experiments demonstrate that the proposed framework can achieve a better data removal effect than the state-of-the-art frameworks, marking a significant stride towards trustworthy federated unlearning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_15917 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Blockchain-enabled Trustworthy Federated Unlearning Lin, Yijing Gao, Zhipeng Du, Hongyang Ren, Jinke Xie, Zhiqiang Niyato, Dusit Machine Learning Cryptography and Security Federated unlearning is a promising paradigm for protecting the data ownership of distributed clients. It allows central servers to remove historical data effects within the machine learning model as well as address the "right to be forgotten" issue in federated learning. However, existing works require central servers to retain the historical model parameters from distributed clients, such that allows the central server to utilize these parameters for further training even, after the clients exit the training process. To address this issue, this paper proposes a new blockchain-enabled trustworthy federated unlearning framework. We first design a proof of federated unlearning protocol, which utilizes the Chameleon hash function to verify data removal and eliminate the data contributions stored in other clients' models. Then, an adaptive contribution-based retraining mechanism is developed to reduce the computational overhead and significantly improve the training efficiency. Extensive experiments demonstrate that the proposed framework can achieve a better data removal effect than the state-of-the-art frameworks, marking a significant stride towards trustworthy federated unlearning. |
| title | Blockchain-enabled Trustworthy Federated Unlearning |
| topic | Machine Learning Cryptography and Security |
| url | https://arxiv.org/abs/2401.15917 |