Abstract
The capacity of federated learning (FL) to tackle the issue of “Data Island” while maintaining data privacy has garnered significant attention. Nonetheless, semi-trusted cloud platforms can infer the actual data distribution of local users via intermediate characteristics such as gradients. The blockchain proposal has resolved the challenge of consistency in decentralized data sharing. It is difficult to guarantee the accuracy of the block’s data based on the existing study. To address this issue, we present a federated consensus mechanism that is both efficient and protective of privacy (FedBC). This approach can effectively limit the impact of Byzantine nodes on consistency and accuracy. During this procedure, crucial intermediate parameters, such as the gradient of the data owner, will not leak. Specifically, we proposed a gradient-similarity-based secure consensus technique (SecPBFT) to minimize Byzantine gradients. All nodes transmit the DO sub-gradients during each consensus round and cluster and partition the sub-gradients in the consensus with care. Then, the dynamic elimination of Byzantine gradients in each round of the consensus procedure is accomplished. Theoretically, we demonstrated the scheme’s security and confirmed the scheme’s efficacy. FedBC’s attack success rate is at least 50% lower than if no defense mechanisms were in place.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Achituve, I., Shamsian, A., Navon, A., Chechik, G., Fetaya, E.: Personalized federated learning with gaussian processes. Adv. Neural Inf. Process. Syst. 34 (2021)
Buterin, V., Reijsbergen, D., Leonardos, S., Piliouras, G.: Incentives in Ethereum’s hybrid Casper protocol. Int. J. Netw. Manag. 30(5), e2098 (2020)
Büyüközkan, G., Tüfekçi, G.: A decision-making framework for evaluating appropriate business blockchain platforms using multiple preference formats and VIKOR. Inf. Sci. 571, 337–357 (2021)
Chen, H., Liang, M., Liu, W., Wang, W., Liu, P.X.: An approach to boundary detection for 3D point clouds based on DBSCAN clustering. Pattern Recogn. 124, 108431 (2022)
Chen, J., Zhang, X., Zhang, R., Wang, C., Liu, L.: De-Pois: an attack-agnostic defense against data poisoning attacks. IEEE Trans. Inf. Forensics Secur. 16, 3412–3425 (2021)
Cohen, G., Afshar, S., Tapson, J., Van Schaik, A.: EMNIST: extending MNIST to handwritten letters. In: 2017 International Joint Conference on Neural Networks (IJCNN), pp. 2921–2926. IEEE (2017)
Consulting, I.: General data protection regulation-official (2016). https://gdpr-info.eu/
Feng, C., Liu, B., Yu, K., Goudos, S.K., Wan, S.: Blockchain-empowered decentralized horizontal federated learning for 5G-enabled UAVs. IEEE Trans. Ind. Inf. 18(5), 3582–3592 (2021)
Feng, Y., Zhang, W., Luo, X., Zhang, B.: A consortium blockchain-based access control framework with dynamic orderer node selection for 5G-enabled industrial IoT. IEEE Trans. Ind. Inf. 18(4), 2840–2848 (2021)
Guerraoui, R., Rouault, S., et al.: The hidden vulnerability of distributed learning in Byzantium. In: International Conference on Machine Learning, pp. 3521–3530. PMLR (2018)
Hou, L., Xu, X., Zheng, K., Wang, X.: An intelligent transaction migration scheme for raft-based private blockchain in internet of things applications. IEEE Commun. Lett. 25(8), 2753–2757 (2021)
Jia, B., Zhang, X., Liu, J., Zhang, Y., Huang, K., Liang, Y.: Blockchain-enabled federated learning data protection aggregation scheme with differential privacy and homomorphic encryption in IIoT. IEEE Trans. Ind. Inform. (2021)
Lax, G., Russo, A., Fascì, L.S.: A blockchain-based approach for matching desired and real privacy settings of social network users. Inf. Sci. 557, 220–235 (2021)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Li, W., Feng, C., Zhang, L., Xu, H., Cao, B., Imran, M.A.: A scalable multi-layer PBFT consensus for blockchain. IEEE Trans. Parallel Distrib. Syst. 32(5), 1146–1160 (2020)
Liu, X., Li, H., Xu, G., Chen, Z., Huang, X., Lu, R.: Privacy-enhanced federated learning against poisoning adversaries. IEEE Trans. Inf. Forensics Secur. 16, 4574–4588 (2021)
Ma, Z., Ma, J., Miao, Y., Li, Y., Deng, R.H.: ShieldFL: mitigating model poisoning attacks in privacy-preserving federated learning. IEEE Trans. Inf. Forensics Secur. 17, 1639–1654 (2022)
Ouyang, L., Yuan, Y., Cao, Y., Wang, F.Y.: A novel framework of collaborative early warning for COVID-19 based on blockchain and smart contracts. Inf. Sci. 570, 124–143 (2021)
Rodler, M., Li, W., Karame, G.O., Davi, L.: \(\{\)EVMPatch\(\}\): timely and automated patching of Ethereum smart contracts. In: 30th USENIX Security Symposium (USENIX Security 2021), pp. 1289–1306 (2021)
Su, L., et al.: Evil under the sun: understanding and discovering attacks on Ethereum decentralized applications. In: 30th USENIX Security Symposium (USENIX Security 2021), pp. 1307–1324 (2021)
Torres, C.F., Camino, R., et al.: Frontrunner jones and the raiders of the dark forest: an empirical study of frontrunning on the Ethereum blockchain. In: 30th USENIX Security Symposium (USENIX Security 21), pp. 1343–1359 (2021)
Weerasinghe, S., Alpcan, T., Erfani, S.M., Leckie, C.: Defending support vector machines against data poisoning attacks. IEEE Trans. Inf. Forensics Secur. 16, 2566–2578 (2021)
Wen, J., Zhao, B.Z.H., Xue, M., Oprea, A., Qian, H.: With great dispersion comes greater resilience: efficient poisoning attacks and defenses for linear regression models. IEEE Trans. Inf. Forensics Secur. 16, 3709–3723 (2021)
Xie, C., Chen, M., Chen, P.Y., Li, B.: CRFL: certifiably robust federated learning against backdoor attacks. In: International Conference on Machine Learning, pp. 11372–11382. PMLR (2021)
Yin, D., Chen, Y., Kannan, R., Bartlett, P.: Byzantine-robust distributed learning: towards optimal statistical rates. In: International Conference on Machine Learning, pp. 5650–5659. PMLR (2018)
Acknowledgment
This work was supported by the National Natural Science Foundation of China (62125205), the Natural Science Basic Research Plan in Shaanxi Province (2022JQ-594).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Xu, M., Li, X. (2022). FedBC: An Efficient and Privacy-Preserving Federated Consensus Scheme. In: Chen, X., Huang, X., Kutyłowski, M. (eds) Security and Privacy in Social Networks and Big Data. SocialSec 2022. Communications in Computer and Information Science, vol 1663. Springer, Singapore. https://doi.org/10.1007/978-981-19-7242-3_10
Download citation
DOI: https://doi.org/10.1007/978-981-19-7242-3_10
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-7241-6
Online ISBN: 978-981-19-7242-3
eBook Packages: Computer ScienceComputer Science (R0)