Real-Time Network Packet Sniffer

MCA

The rapid increase in the volume of network traffic and the growing complexity of cyberattacks require sophisticated tools to monitor networks and ensure security. Conventional packet sniffers, although strong, tend to be devoid of real-time analysis functions, are weak in handling encrypted traffic, and do not respond well to zero-day attacks. This paper introduces the design, implementation, and assessment of a Real-Time Packet Sniffer system that combines traditional packet examination with machine learning (ML) to perform smarter traffic analysis and anomaly identification. Created in Python with the Scapy library, the tool intercepts real-time network packets, extracts relevant features (protocol, source/destination IP, packet length), and analyzes them for real-time visualization through an interactive Streamlit dashboard. The major contribution of this research is the introduction of proposed integration of ML models such as LightGBM and CNN to classify traffic and detect malicious patterns, going beyond signature-based detection. The system was thoroughly tested for both functional and non-functional requirements and showed excellent packet capture accuracy, light resource usage, and good visualization. The findings show that the suggested system is an affordable, scalable, and user-friendly solution for educational and professional network security monitoring, which presents a solid base for future extensions such as deep packet inspection and cloud-distributed analysis.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.