The project proposes an intrusion detection scheme for IoT networks that classifies traffic flow through the application of deep learning concepts.
We adopted a newly published IoT dataset (Bot-IoT dataset) and generated generic features from the field information in packet level. We developed a feed-forward neural networks model for binary and multi-class classification including denial of service, distributed denial of service, reconnaissance and information theft attacks against IoT devices.
- TensorFlow
- Dataset by the Cyber Range Lab of the center of UNSW Canberra Cyber: https://www.unsw.adfa.edu.au/unsw-canberra-cyber/cybersecurity/ADFA-NB15-Datasets/bot_iot.php