Supervised Learning Approach for Intrusion Detection in Unbalanced Network Traffic

Intrusion detection systems (IDS) serve as critical sentinels in network security, assuming a paramount role in identifying and mitigating potential threats. With the evolution of our digital landscape, robust and productive intrusion detection mechanisms have become increasingly imperative. The significance of IDS lies in their ability to safeguard network resources’ integrity, confidentiality, and availability. In an era where cyber threats constantly evolve in complexity and scale, IDS serves as the front line of defence, tirelessly monitoring network traffic to pinpoint suspicious activities and mitigate potential security breaches. To address the class imbalance problem, the Synthetic Minority Over-sampling Technique (SMOTE) was applied to pre-process the CIC-IDS 2017 and NSL-KDD 2009 datasets. Advanced machine learning technique is harnessed to enhance IDS capabilities, specifically through utilising Support Vector Machines (SVM) for subsequent classification tasks. The experimental outcomes on both datasets unveil exceptional accuracy of 99% and performance across multiple intrusion types, underscoring the effectiveness of our SVM-based approach in strengthening IDS.