Intelligent Network Intrusion Detection System

This research successfully presents a lightweight and efficient Intrusion Detection and Prevention System developed using Python. The system is capable of capturing live network traffic, analyzing protocols, detecting malicious activities, and taking preventive actions in real time. By integrating components such as packet capture, protocol analysis, detection engine, alert system, and prevention module, the system provides a complete security solution for small-scale networks. One of the major achievements of this work is its ability to detect common types of attacks, including Denial of Service (DoS), ICMP flooding, HTTP anomalies, and DNS misuse. The system demonstrates reliable performance while maintaining low computational overhead, making it suitable for environments with limited resources. This lightweight nature ensures that the system can be deployed in educational labs, small organizations, and experimental setups without requiring high-end hardware. The evaluation of the system using performance metrics such as accuracy, False Positive Rate (FPR), and F1 Score indicates that the detection mechanism is effective for known attack patterns. However, the results also highlight the importance of improving detection techniques to handle more complex and evolving threats. The current rule-based approach provides a strong foundation, but its limitations emphasize the need for more advanced solutions. Overall, the proposed IDPS achieves a balance between simplicity, efficiency, and functionality. It serves as a valuable learning tool for understanding the working principles of intrusion detection systems while also providing a practical implementation that can be extended further. The project demonstrates that even a lightweight system, when designed logically, can contribute significantly to network security.

 [1] A. Pinto, L.-C. Herrera, Y. Donoso, and J. A. Gutierrez, “Survey on intrusion detection systems based on machine learning techniques for the protection of critical infrastructure,” Sensors, vol. 23, no. 5, p. 2415, Feb. 2023. [2] N. Moustafa, B. Turnbull, and K.-K. R. Choo, “An ensemble intrusion detection technique based on statistical flow features for protecting IoT network traffic,” IEEE Internet of Things Journal, vol. 6, no. 3, pp. 4815–4830, Jun. 2019. [3] A. Khraisat, I. Gondal, P. Vamplew, J. Kamruzzaman, and A. Alazab, “A novel hybrid ensemble intrusion detection system for detecting IoT attacks,” Electronics, vol. 8, no. 11, p. 1210, Oct. 2019. [4] S. Rajagopal, P. P. Kundapur, and K. S. Hareesha, “A stacking ensemble approach for network intrusion detection using heterogeneous datasets,” Security and Communication Networks, vol. 2020, pp. 1–9, Jan. 2020. [5] W. Ma, H. Qu, and J. Zhao, “Traffic network prediction using recursive algorithm with correntropy and forgetting factor,” in Proc. 25th Chinese Control and Decision Conf. (CCDC), Guiyang, China, May 2013, pp. 490–494. [6] N. Koroniotis, N. Moustafa, E. Sitnikova, and B. Turnbull, “Towards realistic botnet dataset generation in IoT environments: The Bot-IoT dataset,” Future Generation Computer Systems, vol. 100, pp. 779–796, Nov. 2019. [7] D. H. Wolpert, “Stacked generalization,” Neural Networks, vol. 5, no. 2, pp. 241–259, Jan. 1992. [8] M. J. van der Laan, E. C. Polley, and A. E. Hubbard, “Super learner,” Statistical Applications in Genetics and Molecular Biology, vol. 6, no. 1, Jan. 2007. [9] Ms. Shiksha, “Project Supervision and Technical Guidance for Intelligent Network Intrusion Detection System,” B.Tech Project, 2026.