Device Fingerprinting using Deep Convolutional Neural Networks
Device identification using network traffic analysis is being researched for IoT and non-IoT devices against cyber-attacks. The idea is to define a device specific unique fingerprint by analyzing the solely inter-arrival time (IAT) of packets as feature to identify a device. Deep learning is used on IAT signature for device fingerprinting of 58 non-IoT devices. We observed maximum recall and accuracy of 97.9% and 97.7% to identify device. A comparitive research GTID found using defined IAT signature that models of device identification are better than device type identification. However, in this research, device type identification models performed better than device identification. We observed 1.5% improvement in device identification and 23% improvement in device type identification over GTID with deep convolutional neural network learning. We observed that when deep learning models are attacked over device signature, the model identifies the change in signature and classifies the device in the wrong class thereby the performance of the model degrades, indicating the system under attack.
All instructions are available at https://github.com/naneja/device-fingerprinting