Case study

IoT Intrusion Detection System (TCNN)

An intelligent intrusion detection system for IoT devices — deep-learning anomaly detection wrapped in a full-stack application.

Problem

IoT devices are easy targets: limited compute, weak defaults, and constant network exposure. Detecting attacks against them means analyzing traffic patterns and separating real anomalies from normal network chatter.

Approach

• A packet scanner captures live network traffic from IoT devices for analysis.
• Traffic is preprocessed with Pandas and NumPy into features suitable for model input, with Matplotlib used for evaluation and tuning visualizations.
• A Temporal Convolutional Neural Network (TCNN), built on Python's deep-learning stack with scikit-learn, classifies traffic and flags anomalies.
• A Django backend serves the model's detections to a React frontend, turning the pipeline into a usable end-to-end application.

Outcome

• Detected multiple attack classes against IoT devices, including DoS, DDoS, and identity theft.
• Deployed as a working application — capture, detection, and presentation in one system.

Stack