BLOCK HUNTER FEDERATED LEARNING FOR CYBER THREAT HUNTING IN BLOCKCHAIN-BASED IIOT NETWORKS

Abstract

Nowadays, blockchain-based technologies are being developed in various industries to 
improve data security. In the context of the Industrial Internet of Things (IIoT), a chain-based 
network is one of the most notable applications of blockchain technology. IIoT devices have become 
increasingly prevalent in our digital world, especially in support of developing smart factories. 
Although blockchain is a powerful tool, it is vulnerable to cyber attacks. Detecting anomalies in 
blockchain-based IIoT networks in smart factories is crucial in protecting networks and systems from 
unexpected attacks. In this paper, we use Federated Learning (FL) to build a threat hunting framework 
called Block Hunter to automatically hunt for attacks in blockchain-based IIoT networks. Block 
Hunter utilizes a cluster-based architecture 
for anomaly detection combined with several machine learning models in a federated environment. 
To the best of our knowledge, Block Hunter is the first federated threat hunting model in IIoT 
networks that identifies anomalous behavior while preserving 
privacy. Our results prove the efficiency of the Block Hunter in detecting anomalous activities with 
high accuracy and minimum required bandwidth.