The Future of Cyber Defence: ML and DL Enhanced Firewalls for Intrusion Detection
Vishnu Kant, Kanwarpartap Singh Gill, Mukesh Kumar, Ruchira Rawat · 2024
Given the increasing frequency of network-based threats, there is a critical need for robust intrusion detection systems (IDS) to safeguard digital assets. Traditional rule-based IDS often struggle to counter emerging cyber threats, highlighting the demand for more adaptive solutions. This study introduces the Next Generation Firewall (NGFW), an advanced firewall system enhanced by machine learning (ML) and deep learning (DL) techniques. By integrating ML algorithms like Support Vector Machines (SVM), Random Forests, and Deep Neural Networks (DNN) with DL models such as Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN), the NGFW significantly improves detection flexibility, effectiveness, and accuracy. Our comprehensive literature review demonstrates the substantial impact of ML and DL on IDS performance. The NGFW's approach includes systematic data collection, preprocessing, feature extraction, and rigorous model evaluation using metrics like accuracy, precision, and recall. Experimental results show that CNNs excel in detecting malicious activities with minimal false positive rates. Real-world testing further validates the NGFW's capacity to strengthen cybersecurity measures. The classification report reveals impressive performance, with precision, recall, and F1-scores exceeding 97% in each category and an overall accuracy of 97.29%. These results underscore the potential of ML and DL to advance intelligent cybersecurity solutions and enhance the reliability of intrusion detection systems.