AI-Enhanced Firewalls: Empowering Intrusion Detection with ML and DL
Gurnimarjit Singh, Kanwarpartap Singh Gill · 2024
Given the increasing frequency of network-based threats, strong intrusion detection systems (IDS) are essential for safeguarding digital assets. Traditional rule-based IDS often struggle to keep up with evolving cyber threats, highlighting the need for more adaptive solutions. This study introduces a Next Generation Firewall (NGFW), which integrates machine learning and deep learning techniques to improve IDS performance. By employing ML algorithms like Support Vector Machines (SVM), Random Forests, and Deep Neural Networks (DNN), alongside DL models such as Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN), the NGFW significantly enhances detection capabilities, flexibility, and accuracy. A comprehensive review of the literature demonstrates the effectiveness of ML and DL in IDS. The proposed approach involves systematic data collection, preprocessing, feature extraction, and model evaluation using metrics such as accuracy, precision, and recall. Experimental results show that CNNs achieve particularly low false-positive rates when detecting malicious activities. Additional real-world testing further validates the NGFW’s role in strengthening cybersecurity defenses. The classification report achieved high precision, recall, and F 1 -scores above 97 percent across all categories, with an overall accuracy of 97.29 percent. These findings advocate for further research into intelligent cyber defenses, emphasizing the value of ML and DL in developing more adaptable and resilient IDS.