Open Access
Subscription Access
Multilayered Framework for Enhancing Data Confidentiality, Integrity, and Threat Detection through Blockchain, Advanced Cryptography, and Machine Learning
Recent developments in the Internet of Things (IoT) have significantly expanded the interconnectedness of devices, leading to an increased need for strong security mechanisms. However, the proliferation of IoT networks has introduced critical vulnerabilities, particularly in data handling and storage, which are susceptible to unauthorized access, tampering, and malicious attacks. Addressing these challenges, this study proposes a multilayered Security Model for IoT that integrates advanced cryptographic techniques, blockchain technology, and machine learning algorithms to ensure the secrecy, integrity, and availability of data within IoT networks. The proposed model employs blockchain technology for decentralized, immutable data storage, effectively mitigating risks associated with unauthorized access and data tampering. Additionally, the model includes a deep learning-based malicious detection system, powered by a Convolutional Neural Network (CNN) in conjunction with the Q-Learning based Whale Optimization Algorithm (Q-WOA), to identify and counteract potential threats within the network. The result shows that the proposed CNN-QWOA models exceed others in most metrics. The proposed CNNQ-WOA model excels accuracy with 0.965, which is higher than the others, leading to the higher overall correct prediction rate.
Keywords
Data Confidentiality, Data Integrity, Threat Detection, Blockchain, Advanced Cryptography, Machine Learning.
User
Font Size
Information
Abstract Views: 19