A comparative analysis of Network Intrusion Detection (NID) using Artificial Intelligence techniques for increase network security

Network Intrusion Detection Systems (NIDS) are critical components of modern cybersecurity frameworks, designed to detect and mitigate malicious activities within networks. This study explores the application of Artificial Intelligence (AI) techniques, including Machine Learning (ML) and DL, for improving network security through accurate intrusion detection. Using the CIS-CICIDS2017 dataset, a comprehensive preprocessing pipeline involving data cleaning, SMOTE-based balancing, Min-Max normalization, and feature selection was employed. The Random Forest (RF) model demonstrated superior performance with an accuracy99.90%, precision97.78%, recall97.08%, and an F1-score97.41%. Comparative analysis with Decision Tree (DT), Stacked LSTM, and AdaBoost models highlighted RF's robustness in detecting and classifying network traffic. Future research aims to optimize feature engineering and explore hybrid AI models for improved real-time intrusion detection in dynamic network environments.