HTTP Botnet Detection in IOT Devices using Network Traffic Analysis

Internet of Things (IoT) is a global network infrastructure linking physical and virtual objects through the exploitation of data capture and communication capabilities. Providing security in the IoT environment is a very challenging task. Malware attacks are very common in IoT, which lead to creation of IoT botnets. In this work, we perform behavioural analysis to detect the bot-nets using http based C&C Servers in the IOT environment. The results can help us know the potential of applying Machine Learning algorithms to the IoT network behaviour dataset. We also explore the advantages of using the behavioural approach instead of signature-based bot-net detection. Feature selection is important since it helps in optimizing Machine Learning algorithms to focus only on those features, which are influenced by the activities of a bot-net.