Anomaly-based intrusion detection system based on feature selection and majority voting

Recently, cyberattacks have been more complex than in the past, as a new cyber-attack is initiated almost every day. Therefore, researchers should develop efficient intrusion detection systems (IDS) to detect cyber-attacks. In order to improve the detection and prevention of the aforementioned cyber-attacks, several articles developed IDSs exploiting machine learning and deep learning. In this paper, a way to find network intrusions using a combination of feature selection and adoptive voting is investigated. NSL-KDD dataset, a high-dimensional dataset that has been widely used for network intrusion detection, is applied in this approach. Feature selection plays an important role for improving accuracy and testing time as it eliminates the less significant attributes from the data set, thus saving computational power and effort. The experimental results show that the proposed approach achieves an accuracy of 86.5% on the NSL-KDD test dataset using an adoptive voting algorithm trained with the selected features. In addition, the time to process each record is 97.5 microseconds, which reflects the proposed model's superior performance. Comparing the proposed model with the existing models in the literature shows that the proposed adaptive voting approach significantly improves intrusion detection accuracy, enhances computational efficiency, and reduces false positives.