Location
Online
Event Website
https://hicss.hawaii.edu/
Start Date
4-1-2021 12:00 AM
End Date
9-1-2021 12:00 AM
Description
The Internet of Things (IoT) and Industrial IoT (IIoT) is enabled by Wireless Personal Area Network (WPAN) devices. However, these devices increase vulnerability concerns of the IIoT and resultant Critical Infrastructure (CI) risks. Secure IIoT is enabled by both pre-attack security and post-attack forensic analysis. Radio Frequency (RF) Fingerprinting enables both pre- and post-attack security by providing serial-number level identification of devices through fingerprint characterization of their emissions. For classification and verification, research has shown high performance by employing the neural network-based Generalized Relevance Learning Vector Quantization-Improved (GRLVQI) classifier. However, GRLVQI has numerous hyperparameters and tuning requires AI expertise, thus some researchers have abandoned GRLVQI for notionally simpler, but less accurate, methods. Herein, we develop a fool-proof approach for tuning AI algorithms. For demonstration, Z-Wave, an insecure low-power/cost WPAN technology, and the GRLVQI classifier are considered. Results show significant increases in accuracy (5% for classification, 50% verification) over baseline methods.
Tuning Hyperparameters for DNA-based Discrimination of Wireless Devices
Online
The Internet of Things (IoT) and Industrial IoT (IIoT) is enabled by Wireless Personal Area Network (WPAN) devices. However, these devices increase vulnerability concerns of the IIoT and resultant Critical Infrastructure (CI) risks. Secure IIoT is enabled by both pre-attack security and post-attack forensic analysis. Radio Frequency (RF) Fingerprinting enables both pre- and post-attack security by providing serial-number level identification of devices through fingerprint characterization of their emissions. For classification and verification, research has shown high performance by employing the neural network-based Generalized Relevance Learning Vector Quantization-Improved (GRLVQI) classifier. However, GRLVQI has numerous hyperparameters and tuning requires AI expertise, thus some researchers have abandoned GRLVQI for notionally simpler, but less accurate, methods. Herein, we develop a fool-proof approach for tuning AI algorithms. For demonstration, Z-Wave, an insecure low-power/cost WPAN technology, and the GRLVQI classifier are considered. Results show significant increases in accuracy (5% for classification, 50% verification) over baseline methods.
https://aisel.aisnet.org/hicss-54/st/digital_forensics/5