Binary Linear Tree Commitment-based Ownership Protection for Distributed Machine Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916088381440000 |
|---|---|
| author | Xie, Tianxiu Gai, Keke Yu, Jing Zhu, Liehuang |
| author_facet | Xie, Tianxiu Gai, Keke Yu, Jing Zhu, Liehuang |
| contents | Distributed machine learning enables parallel training of extensive datasets by delegating computing tasks across multiple workers. Despite the cost reduction benefits of distributed machine learning, the dissemination of final model weights often leads to potential conflicts over model ownership as workers struggle to substantiate their involvement in the training computation. To address the above ownership issues and prevent accidental failures and malicious attacks, verifying the computational integrity and effectiveness of workers becomes particularly crucial in distributed machine learning. In this paper, we proposed a novel binary linear tree commitment-based ownership protection model to ensure computational integrity with limited overhead and concise proof. Due to the frequent updates of parameters during training, our commitment scheme introduces a maintainable tree structure to reduce the costs of updating proofs. Distinguished from SNARK-based verifiable computation, our model achieves efficient proof aggregation by leveraging inner product arguments. Furthermore, proofs of model weights are watermarked by worker identity keys to prevent commitments from being forged or duplicated. The performance analysis and comparison with SNARK-based hash commitments validate the efficacy of our model in preserving computational integrity within distributed machine learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_05895 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Binary Linear Tree Commitment-based Ownership Protection for Distributed Machine Learning Xie, Tianxiu Gai, Keke Yu, Jing Zhu, Liehuang Machine Learning Artificial Intelligence Cryptography and Security Distributed, Parallel, and Cluster Computing Distributed machine learning enables parallel training of extensive datasets by delegating computing tasks across multiple workers. Despite the cost reduction benefits of distributed machine learning, the dissemination of final model weights often leads to potential conflicts over model ownership as workers struggle to substantiate their involvement in the training computation. To address the above ownership issues and prevent accidental failures and malicious attacks, verifying the computational integrity and effectiveness of workers becomes particularly crucial in distributed machine learning. In this paper, we proposed a novel binary linear tree commitment-based ownership protection model to ensure computational integrity with limited overhead and concise proof. Due to the frequent updates of parameters during training, our commitment scheme introduces a maintainable tree structure to reduce the costs of updating proofs. Distinguished from SNARK-based verifiable computation, our model achieves efficient proof aggregation by leveraging inner product arguments. Furthermore, proofs of model weights are watermarked by worker identity keys to prevent commitments from being forged or duplicated. The performance analysis and comparison with SNARK-based hash commitments validate the efficacy of our model in preserving computational integrity within distributed machine learning. |
| title | Binary Linear Tree Commitment-based Ownership Protection for Distributed Machine Learning |
| topic | Machine Learning Artificial Intelligence Cryptography and Security Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2401.05895 |