BRDO: Blockchain Assisted Intrusion Detection Using Optimized Deep Stacked Network

• Published in: Cybernetics and systems Vol. ahead-of-print; no. ahead-of-print; pp. 1 - 22
• Main Authors: N, Kumaran, J S, Shyam Mohan
• Format: Journal Article
• Language: English
• Published: Taylor & Francis 31.01.2023
• Subjects: Battle royale optimization; Dingo optimizer; Intrusion detection; network attacks; security; supply chain management
• ISSN: 0196-9722; 1087-6553
• DOI: 10.1080/01969722.2023.2175153

The blockchain model exposed its adaptability in various areas, including inter-banking, supply chain management, international payment, etc. The anomaly intrusion in blockchain mostly threatens the privacy and security of information, thus secure intrusion detection technique is highly essential. Presently, blockchain is incorporated into intrusion detection model for improving the overall system performance. However, the existing methods are not sufficient for detecting recent network attacks. Therefore, the blockchain-enabled intrusion detection is developed in this paper based on the Battle Royale Dingo optimization (BRDO) driven deep stacked network model. Here, a deep stacked network is applied for detecting the intrusion, and it is trained based on the optimization model for enhancing detection performance. The designed BRDO-based deep stacked network achieved improved performance than traditional techniques with regards to testing accuracy, True Positive Rate (TPR), and False Positive Rate (FPR) of 0.9106, 0.9180, and 0.9186.