A Visualized Botnet Detection System Based Deep Learning for the Internet of Things Networks of Smart Cities

Abstract

Internet of Things applications for smart cities have currently become a primary target for advanced persistent threats of botnets. This article proposes a botnet detection system based on a two-level deep learning framework for semantically discriminating botnets and legitimate behaviors at the application layer of the domain name system (DNS) services. In the first level of the framework, the similarity measures of DNS queries are estimated using siamese networks based on a predefined threshold for selecting the most frequent DNS information across Ethernet connections. In the second level of the framework, a domain generation algorithm based on deep learning architectures is suggested for categorizing normal and abnormal domain names. The framework is highly scalable on a commodity hardware server due to its potential design of analyzing DNS data. The proposed framework was evaluated using two datasets and was compared with recent deep learning models. Various visualization methods were also employed to understand the characteristics of the dataset and to visualize the embedding features. The experimental results revealed substantial improvements in terms of F1-score, speed of detection, and false alarm rate.