AN ENHANCED MACHINE LEARNING AND BLOCKCHAIN-BASED FRAMEWORK FOR SECURE AND DECENTRALIZED ARTIFICIAL INTELLIGENCE APPLICATIONS IN 6G NETWORKS USING ARTIFICIAL NEURAL NETWORKS (ANNS)
Keywords:
Blockchain, 6G Networks, wireless Network, security management, machine learning Deep neural Network, CNN, Healthcare, Prediction modelsAbstract
Artificial Intelligence (AI) and especially Machine Learning (ML) can play a very important role in realizing and optimizing 6G Network applications. 6G mobile Network technology will establish new benchmarks necessary for achieving unreasonable performance targets that exceed what 5G Networks can deliver. The performance targets which 5G Networks cannot achieve make 6G mobile technology necessary. The current limitations of 5G Networking become evident when more Networks become operational. More widespread 5G Network deployments encourage the study of 6G Networks because of their increased installation rates. Studies in this investigation cover essential aspects of privacy security alongside them. Security issues related to 6G technology. Maintaining a real-time system requires wireless monitoring to be secure. Sensor Networks (WSNs). The security vulnerability known as denial of service represents a major threat to Networks. The DoS attacks that WSNs encounter pose serious risks because they harm their complete operational system. This research proposes a novel Blockchain and Machine Learning based infrastructure (KSI) hash chain for 6G technology that enables Network security optimization through this new proposed method. A machine learning model for the 6G Network security system is implemented during this research. The blockchain user datagram transport protocol integrates reinforcement management methods to operate security function. Subsequent operations for Network optimization are accomplished through artificial democracy. The outcomes of simulation tests used different Network parameters. The Network evaluation relies on measurements of throughput together with energy efficiency packet delivery ratio and end–to–end delay parameters. The system provides a capability to determine optimal node and path selection which minimizes Network traffic. The proposed technique obtained 97% throughput, 95% energy efficiency, 96% accuracy, 50% send–to–end delay,and 94% packet delivery ratio.
