NIDS Intrusion Detection System
Network SecurityNetwork Intrusion Detection System
Lead Developer · 2023.09 – 2024.03
Project details:
- Built a machine learning–based network intrusion detection system using a Random Forest algorithm to classify network traffic in real time.
- Detected multiple attack vectors including DoS, Probe, R2L, and U2R, enabling automated analysis of large-scale network traffic.
- Designed a complete backend pipeline for traffic capture, feature extraction, model inference, and alert visualization.
- Delivered a Django-based web console for real-time monitoring and historical data queries.
Key outcomes:
Validated on the KDD Cup 99 dataset, achieving a detection accuracy of 96.99% and an F1-score of 0.97.