Leveraging Blockchain and AI Framework for Enhancing Intrusion Prevention and Detection in Cybersecurity
Dhruv Patel
Abstract
Intrusion detection systems (IDS) must protect sophisticated networks for communication. The primary function of these systems was to detect certain signatures, patterns, and rule infractions. Intruder detection in networks has lately made use of machine learning and deep learning, which are suitable alternatives. This paper proposes a high-performance IDS framework leveraging an Artificial Neural Network (ANN) in conjunction with blockchain technology to enhance detection accuracy and ensure secure data handling. The ANN is trained using the backpropagation algorithm and evaluated through standard metrics. Experimental results demonstrate superior performance, achieving 99.9% accuracy, 99.8% precision, 99.7% recall, and a 99.8% F1-score, significantly outperforming comparative models such as Autoencoder, Naïve Bayes, and Random Forest. Incorporating blockchain adds a secure, decentralized layer to intrusion detection management. Modern cybersecurity settings could use the suggested framework right away. Integrating blockchain technology improves data security and trust, which makes the framework ideal for cybersecurity applications that need real-time responses.