Title: Enhancing Intrusion Detection with Image-Based CNN and CTGAN Synthetic Oversampling
Description:
This project develops an intrusion detection framework using image-based representations of network traffic and CNN-based classification. The NSL-KDD dataset is transformed into image-like feature representations so that convolutional neural networks can learn spatial patterns from network behavior. To address class imbalance, CTGAN-based synthetic oversampling is used to generate additional minority-class samples. The framework supports five-class intrusion classification and evaluates the effect of synthetic data on detection performance. This project contributes to cybersecurity research by combining tabular-to-image transformation, deep learning, and generative oversampling for more balanced intrusion detection.