Distributed Firewall Traffic Filtering and Intrusion Detection Using Snort on pfSense Firewalls with Random Forest Classification

In today's interconnected world, network security is of utmost importance for individuals, corporations, and governments. Traditional security measures are insufficient to counter sophisticated cyber attacks. Intrusion Detection Systems (IDS) have emerged as crucial tools for monitoring network traffic, detecting unauthorized access, data breaches, and malicious activities. To address the complexity of network traffic and enhance detection accuracy, machine learning techniques have become increasingly essential. This paper presents a comprehensive description of an IDS specifically designed for network environments, combining packet sniffing with the power of Random Forest Classification. The proposed system utilizes a primary firewall to redirect Internet traffic to secondary firewalls, safeguarding distinct network segments. Leveraging Snort, a renowned intrusion detection system, in conjunction with Random Forest Classification, enables meticulous filtering and analysis of captured traffic for intrusion detection. The system continuously monitors detected intrusions and promptly alerts network administrators when predefined thresholds are surpassed. Performance evaluation using a comprehensive dataset demonstrates the system's effectiveness in accurately detecting various intrusion types, including port scanning, denial-of-service attacks, and SQL injection. The system achieves high accuracy rates while minimizing false positives. Moreover, the paper highlights the strengths of the system, such as early intrusion detection, prevention of intrusion spread, and reduction of unnecessary network traffic, facilitated by the flexible and scalable nature of the Random Forest Classification approach. The paper concludes by discussing potential avenues for future research and enhancements specifically focused on leveraging Random Forest Classification for intrusion detection in network environments.