ABSTRACT
Currently, training neural networks often requires a large corpus of data from multiple parties. However, data owners are reluctant to share their sensitive data to third parties for modelling in many cases. Therefore, Federated Learning (FL) has arisen as an alternative to enable collaborative training of models without sharing raw data, by distributing modelling tasks to multiple data owners. Based on FL, we premodel sent a novel and decentralized approach to training encrypted models with privacy-preserved data on Blockchain. In our approach, Blockchain is adopted as the machine learning environment where different actors (i.e., the model provider, the data provider) collaborate on the training task. During the training process, an encryption algorithm is used to protect the privacy of data and the trained model. Our experiments demonstrate that our approach is practical in real-world applications.
- Bellare, M., Desai, A., Jokipii, E., & Rogaway, P. (1997, October). A concrete security treatment of symmetric encryption. In Proceedings 38th Annual Symposium on Foundations of Computer Science (pp. 394--403). IEEE.Google ScholarCross Ref
- Bellare, M., & Rogaway, P. (1994, May). Optimal asymmetric encryption. In Workshop on the Theory and Application of of Cryptographic Techniques (pp. 92--111). Springer, Berlin, Heidelberg.Google Scholar
- Benet, J. (2014). Ipfs-content addressed, versioned, p2p file system. arXiv preprint arXiv:1407.3561.Google Scholar
- Bengio, Y. (2009). Learning deep architectures for AI. Foundations and trends® in Machine Learning, 2(1), 1--127.Google Scholar
- Caldas, S., Wu, P., Li, T, Konečný, J., McMahan, H. B, Smith, V., & Talwalkar, A. (2018). Leaf: A benchmark for federated settings. arXiv preprint arXiv:1812.01097.Google Scholar
- Croman, K., Decker, C., Eyal, I., Gencer, A. E., Juels, A., Kosba, A., & Song, D. (2016, February). On scaling decentralized blockchains. In International Conference on Financial Cryptography and Data Security (pp. 106--125). Springer, Berlin, Heidelberg.Google ScholarCross Ref
- Du, W., & Atallah, M. J. (2001, September). Secure multiparty computation problems and their applications: a review and open problems. In Proceedings of the 2001 workshop on New security paradigms (pp. 13--22). ACM.Google ScholarDigital Library
- Dwork, C. (2011). Differential privacy. Encyclopedia of Cryptography and Security, 338--340.Google Scholar
- Gentry, C., & Boneh, D. (2009). A fully homomorphic encryption scheme (Vol. 20, No. 09). Stanford: Stanford University.Google Scholar
- Konečný, J., McMahan, H. B., Yu, F. X, Richtárik, P, Suresh, A. T, & Bacon, D. (2016). Federated learning: Strategies for improving communication efficiency. arXiv preprint arXiv:1610.05492.Google Scholar
- LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. nature, 521(7553), 436.Google Scholar
- Luu, L., Narayanan, V., Zheng, C., Baweja, K, Gilbert, S, & Saxena, P. (2016, October). A secure sharding protocol for open blockchains. In Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security (pp. 17--30). ACM.Google ScholarDigital Library
- McMahan, Brendan, and Daniel Ramage. (2017). "Federated learning: Collaborative machine learning without centralized training data." Google Research Blog.Google Scholar
- Shen, Y., Guo, B., Shen, Y., Duan, X., Dong, X., & Zhang, H. (2016). A pricing model for big personal data. Tsinghua Science and Technology, 21(5), 482--490.Google ScholarCross Ref
- Swan, M. (2015). Blockchain: Blueprint for a new economy. "O'Reilly Media, Inc.".Google Scholar
- Wood, G. (2014). Ethereum: A secure decentralised generalised transaction ledger. Ethereum project yellow paper, 151(2014), 1--32.Google Scholar
- Wu, C., Xiao, J., Huang, G., & Wu, F. (2019). Galaxy Learning-A Position Paper. arXiv preprint arXiv:1905.00753. Date:JuneGoogle Scholar
- Zheng, Z., Xie, S., Dai, H. N., Chen, X., & Wang, H. (2018). Blockchain challenges and opportunities: A survey. International Journal of Web and Grid Services, 14(4), 352--375.Google ScholarCross Ref
Index Terms
- Training Encrypted Models with Privacy-preserved Data on Blockchain
Recommendations
A privacy-preserved blockchain for vehicles in smart societies
AIR '23: Proceedings of the 2023 6th International Conference on Advances in RoboticsData collection from the mobile vehicle is the most vulnerable task. In an open network of vehicles, device identities must be protected. Our work in this paper describes a proof-of-authentication-based blockchain to collect and store data from ...
Overview of Blockchain Data Privacy Protection
BIOTC '21: Proceedings of the 2021 3rd Blockchain and Internet of Things ConferenceBlockchain has the advantages of decentralization and distributed sharing of global ledger, but at the same time, it also has the risk of data privacy leakage. In order to prevent the privacy of blockchain users from being stolen by malicious attackers, ...
SDGchain: When Service Dependency Graph Meets Blockchain to Enhance Privacy
IWSPA '21: Proceedings of the 2021 ACM Workshop on Security and Privacy AnalyticsNowadays, the number of services is increasing which allows users to perform their tasks easily. A huge amount of data is published regularly where the personal data takes the lion's share. In fact, personal data protection remains a big issue as far as ...
Comments