A Lightweight Malware Traffic Classification Method Based on a Broad Learning Architecture

Malware traffic classification (MTC) plays an important role for securing the Internet of Things (IoT). Many machine learning (ML) and deep learning (DL)-based MTC methods have been proposed in recent years. However, the former still requires human intervention, while the latter incurs considerable computation overheads. To address these problems, we propose a broad learning (BL)-aided MTC method (BL-MTC), which is a lightweight and graphics processing unit-free solution with good performance and extremely low cost. The simulation results show that the proposed BL-MTC method not only achieves superior results on the USTC-TFC2016 data set but also exhibits an exponential advantage in computation overhead.