Network intrusion detection using meta-heuristic feature selection and cost-sensitive learning
Ritinder Kaur, Neha Gupta · International Journal of Internet Technology and Secured Transactions · 2023
In contemporary society, networked computers are playing a pivotal role in dissemination of knowledge and critical data in information systems; ensuring its security has become a challenging task for the network administrators and researchers. Machine learning techniques are extensively used in intrusion detection systems to mine out the extensive network data and extrapolate attack patterns. This paper proposes an intrusion detection framework with a combination of diverse attribute selection algorithms and machine learning algorithms to provide effective intrusion detection. Firstly, the model extracts the most relevant attributes using a hybrid meta-heuristic feature selection algorithm and then applies supervised machine learning algorithms to detect the several attack classes with improved detection accuracy, execution time and error rate. This study used NSL-KDD dataset on the proposed CS-CFSMHA framework with AdaBoost ensemble technique. Cost-sensitive classification was applied which improved the minority class accuracy and the overall accuracy to 81.1%.