Published Paper Details:

This project presents the development of an advanced Intrusion Detection System (IDS) that utilizes machine learning algorithms, specifically Random Forest and Linear Regression, to detect and classify diverse network attacks, including Denial of Service (DOS), probe, remote to local, and user to local. The proposed IDS addresses the challenge of imbalanced datasets through effective data balancing techniques, ensuring optimal performance and accurate identification of network threats. To provide real-time insights and monitoring, the IDS integrates a Flask web application that offers interactive visualizations. Network administrators can visualize model performance metrics, detected attack types, and real-time network traffic analysis through user-friendly charts and graphs. The IDS system demonstrates enhanced accuracy in detecting both known and novel attack patterns while minimizing false positives. Its capability to handle complex attack scenarios ensures a robust and reliable defense against emerging threats. By leveraging machine learning algorithms and real-time monitoring, the developed IDS empowers administrators to promptly respond to potential security breaches, thereby bolstering overall network security. In conclusion, this project contributes an effective and efficient IDS solution, providing a comprehensive tool for safeguarding network infrastructures against a wide range of intrusions. Continuous updates and feedback-driven improvements are essential to maintain the IDS's efficacy in an ever-evolving cybersecurity