Network Traffic-Based Hybrid Malware Detection for Smartphone and Traditional Networked Systems

With the widespread use of the Internet in recent times, security remains one of the major concerns. Malware poses security threats to smartphones, computers, and networks. These threats require an urgent need to build an efficient hybrid intrusion detection system, which can detect malware from smartphone and traditional systems, and ensure minimal damage to the resources of an organization. In this paper, we propose an intelligent and self-learning network traffic-based hybrid malware detection approach (HMDA) for smartphones and traditional systems considering features that show a similar trend in the network traffic. The system could be used by an organizational network to detect and mitigate any occurrence of malware-based malicious activity inside the network. The proposed HMDA is implemented using machine learning algorithms. We have used ensemble learners to train the model for the HMDA and achieved an accuracy of 95.7% using XGBoost algorithm. The Android traffic captures collected by running the malware dataset have been made publicly available upon request to authors.