Ensemble Method for Anomaly Detection On the Internet of Things

Abstract

 The internet of things generates various types of data traffic with a very large amount of data traffic which has an impact on security issues, one of which is an attack on the Internet of Things network. In the IoT data traffic flow, which contains various data, it turns out that the portion of attack data traffic is usually smaller than normal traffic. Therefore, the attack detection method must be able to recognize the type of attack on a very large data traffic flow and unbalanced data. High data dimensions and unbalanced data are one of the challenges in detecting attacks. To overcome the large data dimensions, Chi-square was chosen as a feature selection technique. In this study, the ensemble method is proposed to improve the ability to detect anomalies in unbalanced data. To produce an ideal detection method, a combination of several classification algorithms such as Bayes Network, Naive Bayes, REPtree and J48 is used. The CICIDS-2017 dataset is used as experimental data because it has a high data dimension which contains unbalanced data. The test results show that the proposed Ensemble method can improve the performance of anomaly detection for high-dimensional data containing unbalanced data