Transferability Evaluation in WiFi Intrusion Detection Systems Through Machine Learning and Deep Learning Approaches

This project focuses on evaluating the transferability of Wi-Fi Intrusion Detection Systems (WIDS) using both Machine Learning (ML) and Deep Learning (DL) approaches. The models employed in this study include Logistic Regression, Random Forest, Support Vector Machine (SVM), and XGBoost, which are applied to classify network traffic into two primary classes: "Attack" and "No Attack." Each model is trained and evaluated based on its ability to detect intrusions and its adaptability across various datasets, making the system more robust and transferable across different network environments. Logistic Regression and Random Forest are leveraged for their simplicity and efficiency, while SVM and XGBoost are chosen for their strong classification capabilities, particularly in handling complex and high-dimensional data. The models are developed using Python and popular libraries such as scikit-learn and XGBoost, with evaluation metrics including accuracy, precision, recall, and F1-score to assess the performance. This study highlights the potential of combining traditional ML techniques with modern DL approaches to create a more adaptive and reliable Wi-Fi Intrusion Detection System, capable of improving network security and reducing false positives.

Keywords: Wi-Fi Intrusion Detection, Machine Learning, Deep Learning, Logistic Regression, Random Forest, Support Vector Machine, XGBoost, Attack Detection, Network Security, Intrusion Detection Systems, Transferability, Classification.