IoT-Botnet Traffic Detection Based on Deep Forest
Yalian Wu, Xieen He, Xingnian Chen · 2022
In order to further improve the accuracy and efficiency of detecting IoT-Botnet attacks from massive and high-dimensional IoT traffic data with seriously imbalanced class distribution, a botnet traffic detection method based on deep forest is proposed. Firstly, a few dominant features are selected based on the Fisher Score. Then, the multi-grained scanning structure is used to mine more relevant information among low-dimensional features to achieve the purpose of feature enhancement. Finally, the cascade forest performs representation learning and refines the classification layer by layer until the overall performance of the deep forest model converges to the best. The deep forest model is trained and tested on the N_BaIoT dataset, and the results show the deep forest model is not affected by massive and high-dimensional data, its average detection accuracy can reach 99.98% on the imbalanced dataset by using only 6 statistical features.