Abstract
The combination of reputation model and PBFT consensus algorithm is a competitive solution to improve consortium blockchains’ TPS. However, there are still many problems for PBFT with reputation model such as detecting malicious nodes and centralization problem. In this paper, an anomaly detection algorithm base on for machine learning is adopted to detect the malicious nodes in consortium blockchains using PBFT consensus mechanism. And then, the results of anomaly detection are applied to evaluate the reputation value of the node. Besides, random number is used to ensure the randomness and fairness of the PBFT primary node selection in the reputation model. The experimental test shows the anomaly detection model can improve significantly the consensus efficiency of PBFT. The test also shows that the use of random number can effectively avoid the centralization caused by the imbalance of the reputation value growth speed between nodes.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Nakamoto,S.: Bitcoin: A Peer-to-Peer Electric Cash System (2021). https://bitcoin.org/bitcoin.pdf
Huang, B., Cai, L.: Blockchains Decryption: Building a Credit-based Next-Generation Internet, 1st edn. Qinghua University Press, Beijing (2016)
Lamport, L.: The Byzantine Generals Problem, pp. 382–401 (1982)
Castro, M., Liskov, B.: Practical byzantine fault tolerance. In: Symposium on Operating Systems Design & Implementation (1999)
Liu, M.D., Chen, Z.N., Shi, Y.J., et al.: Research progress of blockchains in the field of data security. Chin. J. Comput. 43(1), 1–28 (2020)
Janbi, N.F., Radenkovic, M.: An enhanced Bayesian-based reputation system for P2P file sharing. In: Proceedings of 2017 Computing Conference, Piscataway, pp. 1247–1252. IEEE Press (2017)
Sarah, A., Heba, K., Rasha, A., et al.: Authenticpeer++: a trust management system for P2P networks. In: Proceedings of 11th UK-SIM-AMSS European Modelling Symposium on Computer Modeling and Simulation, Piscataway, pp 191–196. IEEE Press (2017)
Gupta, M., Judge, P., Ammar, M.: A reputation system for P2P networks. In: Proceedings of International Workshop on Network & Operating Systems Support for Digital Audio & Video, New York, pp. 144–152. ACM Press (2003)
Lai, Y.X., Bo, Z.X., Liu, J.: Research on defense against sybil attacks in blockchains based on improved PBFT algorithm. J. Commun. 41(9), 104–117 (2020)
Huang, J.H., Xia, X., Li, Z.C., et al.: Trustworthiness certification mechanism based on dynamic authorization. J. Softw. 30(9), 2593–2607 (2019)
Wang, H.Y., Guo, K.X., Pan, Q.Q.: Byzantine fault-tolerant consensus algorithm based on voting mechanism. J. Comput. Appl. 39(6), 1766–1771 (2019)
Huang, D., Chen, B., Li, L., Ding, Y.: Anomaly detection for consortium blockchains based on machine learning classification algorithm. In: Chellappan, S., Choo, K.-K., Phan, NhatHai (eds.) CSoNet 2020. LNCS, vol. 12575, pp. 307–318. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-66046-8_25
Ahemd, M., Mahmood, A.N., Hu, J.: A survey of network anomaly detection techniques. J. Netw. Comput. Appl. 60, 19–31 (2016)
Liang, J., Chen, J.H., Zhang, X.Q., et al.: Anomaly detection based on one-hot encoding and convolutional neural network. J. Tsinghua University (Nat. Sci. Ed.) 59(07), 523–529 (2019)
Jia, F., Yan, Y., Zhang, J.Q.: Network anomaly detection based on K-means clustering feature reduction. J. Tsinghua Univ. (Nat. Sci. Ed.) 58(02), 137–142 (2018)
Sun, L.: Research on SVM-based abnormal network behavior detection method. M.S. dissertation, Nanjing Univ of Posts and Telecommunications, Jiangsu, China (2018)
Chen, S., Zhu, G.S., Qi, X.Y., et al.: Research on abnormal network traffic detection based on machine learning. Inf. Commun. 180(12), 44–47 (2017)
Pham, T., Lee, S.: Anomaly Detection in Bitcoin Network Using Unsupervised Learning Methods. arXiv: Learning (2016)
Yin, H., Yin, S., Vatrapu, R.: A first estimation of the proportion of cybercriminal entities in the bitcoin ecosystem using supervised machine learning. In: 2017 IEEE International Conference on Big Data (Big Data), Boston, MA, pp. 3690–3699 (2017)
Acknowledgement
This paper was supported by Guangxi Key Research and Development Program (GuikeAB20238026); Guangxi Science and Technology Base and Talent Special Project of China (Guike-AD19110042); Innovation Project of GUET Graduate Education (2021YCXS042).
Author information
Authors and Affiliations
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
Gu, R., Chen, B., Huang, D. (2022). Primary Node Selection Algorithm of PBFT Based on Anomaly Detection and Reputation Model. In: Liu, Q., Liu, X., Chen, B., Zhang, Y., Peng, J. (eds) Proceedings of the 11th International Conference on Computer Engineering and Networks. Lecture Notes in Electrical Engineering, vol 808. Springer, Singapore. https://doi.org/10.1007/978-981-16-6554-7_178
Download citation
DOI: https://doi.org/10.1007/978-981-16-6554-7_178
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-6553-0
Online ISBN: 978-981-16-6554-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)