Automatic Malware Detection with Machine Learning Algorithms in a Smart Office Environment
Minsoo Yeo, Ilsub Bang, Yejin Kim, Abbas Ahmad, Hamza Baqa, JaeSeung Song, Cheolsoo Park · IEIE Transactions on Smart Processing and Computing · 2018
The threat of malware in the Internet of Things (IoT) environment is increasing due to a lack of detectors. This paper proposes a method to predict the intrusion of malware using state-of-the- art machine learning algorithms that can detect malware faster and more accurately, compared with the existing methods (that is, payload, port-based, and statistical methods). A smart office environment was implemented to capture the flow of packet datasets, where malware and normal packets were captured, and 11 features were extracted from them. Four machine learning algorithms (random forest, a support vector machine, AdaBoost, and a Gaussian mixture model-based naïve Bayes classifier) were investigated to implement the automatic malware monitoring system. Random forest and AdaBoost could separate the malware and normal flows perfectly, due to their ensemble structures, which could classify unbalanced and noisy datasets.