User privacy on IoT devices using deep learning

The use of Internet of Things (IoT) devices has been increasing rapidly and with it comes an increase in cyberattacks targeting these devices. One of the most harmful attacks in the IoT ecosystem is botnet-based attacks which are notoriously difficult to defend against. In recent years, many researchers have presented deep learning (DL) methods for identifying and categorizing botnet attacks (BA) in the IoT context. In this work, we propose an effective method for identifying BAs on IoT devices using the N-BaIoT dataset. We developed six models, including DL and hybrid models to identify two frequent and dangerous IoT threats, BASHLITE and Mirai. Our results demonstrate that Transformer model can accurately and efficiently detect botnet-based assaults from a variety of IoT devices with a 99.48% accuracy (Acc) level which outperforms other existing models in the literature. Our study contributes to the growing body of research aimed at developing efficient and accurate methods for detecting botnet-based attacks on IoT devices. The proposed method has significant implications for the security of IoT devices and can help to mitigate the harmful effects of BAs in the IoT ecosystem.