Enhancing Performance of Intrusion detection System in the NSL-KDD Dataset using Meta-Heuristic and Machine Learning Algorithms-Design thinking approach

As our reliance on digital technologies grows, the risk of cyber-attacks and data breaches has become a major concern. The NSL-KDD dataset is widely recognized as a standard for evaluating the effectiveness of Intrusion Detection Systems (IDS) in the field of cyber security. IDS can alert security personnel or automatically respond to detected threats, helping organizations protect their data and systems. In this research, a novel approach was proposed to enhance the performance of IDS in the NSL-KDD dataset using meta-heuristic algorithms and machine learning techniques. Multiple meta-heuristic algorithms were utilized to optimize the hyper-parameters of machine learning models, including Random Forest (RF), Classification and Regression Trees (CART), Support Vector Machine (SVM), and Multilayer Perceptron (MLP). The performance of the IDS was evaluated using metrics such as precision, recall, Fl-score, and accuracy. The results of the experiments showed that the proposed method outperformed existing techniques in accurately and robustly detecting intrusions. This paper highlights the capability of meta-heuristic algorithms in optimizing IDS models and the effectiveness of machine learning-based solutions in addressing cyber security challenges. The challenges in the methodology of this research include selecting appropriate meta-heuristic algorithms and evaluation metrics to optimize the performance of IDS in the NSL-KDD dataset. Additionally, scalability to larger and more complex datasets may be a challenge.