Proactive AI Enhanced Consensus Algorithm with Fraud Detection in Blockchain
Date
2023
Journal Title
Journal ISSN
Volume Title
Publisher
Springer
Abstract
The security and transparency provided to the data in blockchain are unmatchable, with the least instances of system hack or failure reported. With a number of consensus algorithms used in the past and the presence of leader nodes in many of them, it is important to check the leader node’s activities. As the system is large, the usage of artificial intelligence and deep learning methodologies seems the right choice to monitor the leader node’s activities. Hence in this chapter, an algorithm is proposed as to how should the consensus algorithm be modified while adding deep learning techniques to keep track of the leader node’s selection behaviors. It also explains how the system detects and moves back to stability once such a scenario is encountered. Hence in this work, the artificial neural network is used to learn the node selection behavior of the leader node by taking in 5 input parameters: sender ID, receiver ID, transaction amount, sender’s balance, and receiver’s balance. Output is either 0 (not selected into the chain) or 1 (selected into the chain) once trained neurons (each input parameter) are tested for it’s sensitivity to the selection. If it exceeds a threshold value, it is assumed to be biased upon that parameter/s, and further consensus occurs. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
Description
item.page.type
Book chapter
item.page.format
Keywords
Artificial intelligence, Blockchain, Consensus algorithm, Cyber-physical systems, Deep learning, Leader node, Mimic selection behavior, Selection pattern
Citation
Das, V., Cherukuri, A.K., Hu, Q., Kamalov, F., Jonnalagadda, A. (2023). Proactive AI Enhanced Consensus Algorithm with Fraud Detection in Blockchain. In Y. Maleh, M. Alazab & I. Romdhani. (Eds.) Blockchain for Cybersecurity in Cyber-Physical Systems. Advances in Information Security, 102, (pp. 259 - 274). Springer, Cham. https://doi.org/10.1007/978-3-031-25506-9_13