IoT Botnet Anomaly Detection Using Unsupervised Deep Learning

The Internet of Things has become a cutting-edge technology that is continuously evolving in size, connectivity, and applicability. This ecosystem makes its presence felt every aspect our lives, along with all other emerging technologies. Unfortunately, despite the significant benefits brought by IoT, increased attack surface built upon it more critical than ever. Devices have limited resources are not typically created security features. Lately, trend botnet threats transitioning to IoT environment been observed, an army infected devices can expand quickly be used for effective attacks. Therefore, identifying proper solutions securing systems currently important challenging research topic. Machine learning-based approaches promising alternative, allowing identification abnormal behaviors detection paper proposes anomaly-based solution uses unsupervised deep learning techniques identify activities. An empirical evaluation proposed method conducted on both balanced unbalanced datasets assess threat capability. False-positive rate reduction impact system also analyzed. Furthermore, comparison included. experimental results reveal performance method.