Abstract: A scheme for identifying wireless devices by capturing out-of-band information in addition to in-band information from wireless devices for enabling accurate classification of wireless devices. Both the in-band and out-of-band spectrum emissions of the received signal are used to capture hardware signatures and features. These hardware signatures are used to discriminate different wireless devices uniquely and efficiently, even when the devices have the same hardware with significantly reduced distortions. The out-of-band information can be extracted using radios with software defined capabilities. Deep learning-based device classification technique is applied that uses IQ samples collected from the RF signals to efficiently identify and classify high-performing transmitters that have the same, minimally distorted hardware components.

Abstract: A scheme for identifying wireless devices by capturing out-of-band information in addition to in-band information from wireless devices for enabling accurate classification of wireless devices. Both the in-band and out-of-band spectrum emissions of the received signal are used to capture hardware signatures and features. These hardware signatures are used to discriminate different wireless devices uniquely and efficiently, even when the devices have the same hardware with significantly reduced distortions. The out-of-band information can be extracted using radios with software defined capabilities. Deep learning-based device classification technique is applied that uses IQ samples collected from the RF signals to efficiently identify and classify high-performing transmitters that have the same, minimally distorted hardware components.