Enhancing Network Security: Intrusion Detection Systems with Hybridized CNN and DNN Algorithms

Networks are vital in modern life. Cybersecurity is essential for ensuring the security of network information. A comprehensive network monitoring mechanism that detects and identifies all potential technological problems and infrastructure issues on the node. While several existing systems are available, they still encounter challenges in accurately detecting vulnerabilities and effectively reducing vigilance to identify intrusion attacks. The popularity of machine learning (ML) is increasing. An all-encompassing approach to conceptualize inventive infiltration with an unexpected structure. The machine learning approach identifies and differentiates between information derived from expertise and knowledge considered traditional or unorthodox. This research presents a unique method for enhancing intrusion detection using a hybrid algorithm that combines the convolutional neural network (CNN) and deep neural network (DNN). The intended Intrusion Detection System (IDS) paradigm categorizes all packets to identify network intrusions and classify them as either normal or malicious. The accuracy of CNN was much higher than other classifiers, achieving a result of 99.18%. The five commonly used measures for evaluating IDS performance are accuracy, precision, recall, f1-score, and false positive rate (FPR). Ultimately, the research suggests exploring the capabilities of hybrid CNN and DNN algorithms in different network settings. To enhance the practical implementation and acceptance of cybersecurity frameworks, it is recommended to undertake comparison studies with current IDS approaches and consider real-world deployment situations and scalability. This study is anticipated to make a substantial contribution to the subject and is likely to interest both academic and industry practitioners.