A Differentially Private Blockchain-Based Approach for Vertical Federated 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_ | 1866916317781557248 |
|---|---|
| author | Tran, Linh Chari, Sanjay Khan, Md. Saikat Islam Zachariah, Aaron Patterson, Stacy Seneviratne, Oshani |
| author_facet | Tran, Linh Chari, Sanjay Khan, Md. Saikat Islam Zachariah, Aaron Patterson, Stacy Seneviratne, Oshani |
| contents | We present the Differentially Private Blockchain-Based Vertical Federal Learning (DP-BBVFL) algorithm that provides verifiability and privacy guarantees for decentralized applications. DP-BBVFL uses a smart contract to aggregate the feature representations, i.e., the embeddings, from clients transparently. We apply local differential privacy to provide privacy for embeddings stored on a blockchain, hence protecting the original data. We provide the first prototype application of differential privacy with blockchain for vertical federated learning. Our experiments with medical data show that DP-BBVFL achieves high accuracy with a tradeoff in training time due to on-chain aggregation. This innovative fusion of differential privacy and blockchain technology in DP-BBVFL could herald a new era of collaborative and trustworthy machine learning applications across several decentralized application domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_07054 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Differentially Private Blockchain-Based Approach for Vertical Federated Learning Tran, Linh Chari, Sanjay Khan, Md. Saikat Islam Zachariah, Aaron Patterson, Stacy Seneviratne, Oshani Cryptography and Security Emerging Technologies Machine Learning We present the Differentially Private Blockchain-Based Vertical Federal Learning (DP-BBVFL) algorithm that provides verifiability and privacy guarantees for decentralized applications. DP-BBVFL uses a smart contract to aggregate the feature representations, i.e., the embeddings, from clients transparently. We apply local differential privacy to provide privacy for embeddings stored on a blockchain, hence protecting the original data. We provide the first prototype application of differential privacy with blockchain for vertical federated learning. Our experiments with medical data show that DP-BBVFL achieves high accuracy with a tradeoff in training time due to on-chain aggregation. This innovative fusion of differential privacy and blockchain technology in DP-BBVFL could herald a new era of collaborative and trustworthy machine learning applications across several decentralized application domains. |
| title | A Differentially Private Blockchain-Based Approach for Vertical Federated Learning |
| topic | Cryptography and Security Emerging Technologies Machine Learning |
| url | https://arxiv.org/abs/2407.07054 |