AI-Based Network Intrusion Detection System Using Machine Learning

The increasing complexity of cyber threats has made intelligent intrusion detection systems an essential component of modern network security. Traditional signature-based Network Intrusion Detection Systems (NIDS) are effective in identifying known attacks but often fail to detect previously unseen threats and require frequent signature updates. To overcome these limitations, this research presented an AI-Based Network Intrusion Detection System (AI-NIDS) that integrates machine learning with real-time network traffic monitoring.   The proposed framework employs Scapy for live packet capture, extracts relevant network traffic features, and utilizes a Random Forest classifier trained on the NSL-KDD dataset to classify network traffic as either normal or malicious. Upon detecting suspicious activity, the system automatically generates alerts, records intrusion events in SQLite and CSV logs, and updates an interactive Streamlit dashboard for continuous monitoring.   Experimental evaluation demonstrated that the proposed system achieved a classification accuracy of 97.98%, indicating its effectiveness in identifying malicious network traffic while maintaining efficient real-time performance. The modular architecture allows easy integration of additional machine learning models, datasets, and visualization components. Furthermore, the proposed framework provides a practical and cost-effective solution for educational institutions, enterprise networks, and small-to-medium organizations requiring intelligent network security. Overall, the proposed AI-NIDS successfully combines machine learning, live packet monitoring, automated logging, and dashboard visualization into a unified platform that enhances network security through accurate and real-time intrusion detection.  

1.               Tavallaee, M., Bagheri, E., Lu, W., & Ghorbani, A. A., "A Detailed Analysis of the KDD CUP 99 Data Set," IEEE Symposium on Computational Intelligence for Security and Defense Applications, 2009. 2.               Breiman, L., "Random Forests," Machine Learning, 45(1), 5–32, 2001. 3.               Scikit-learn Developers, Scikit-learn Documentation. 4.               Scapy Project Documentation. 5.               Streamlit Documentation. 6.               Pedregosa, F., et al., "Scikit-learn: Machine Learning in Python," Journal of Machine Learning Research, 2011. 7.               McKinney, W., "Data Structures for Statistical Computing in Python," 2010. 8.               Harris, C. R., et al., "Array Programming with NumPy," Nature, 2020. 9.               Python Software Foundation, Python Documentation. 10.           SQLite Documentation.