Distributed Industrial Internet of Things (IIoT) has entirely revolutionized the industrial sector that varies from autonomous industrial processes to automation of processes without human intervention. However, threat hunting and intelligence is the most complex task in distributed IIoT. Besides, there exist no standard architectures for hunting micro services orchestration in distributed IIoT systems. The authors propose an efficient and self-learning autonomous multivector threat intelligence and detection mechanism to proactively defend IIoT systems/networks. Our proposed novel compute unified device architecture-empowered Convolutional LSTM2D (ConvLSTM2D) mechanism is highly scalable with self-optimizing capabilities to proficiently tackle diverse dynamic variants of emerging IIoT sophisticated threats and attacks. For a comprehensive evaluation, the authors employed a current state-of-the-art data set with 21 million instances comprised of varying attack patterns and prevalent threat vectors. Moreover, the proposed technique is compared with our constructed contemporary deep learning (DL)-driven architectures and benchmark algorithms. The proposed mechanism outperforms in terms of detection accuracy with a trivial tradeoff in speed efficiency.
Discussion(0)
No comments yet. Be the first to comment.