Presentation
Time:
M.S. Thesis Defense: Fahmida Afrin
Date:
3:00 pm –
4:00 pm
Avery Hall
Room: 347
Target Audiences:
1144 T St
Lincoln NE 68508
Lincoln NE 68508
Additional Info: AVH
M.S. Thesis Defense: Fahmida Afrin
Thursday, July 27, 2023
3:00 PM
347 Avery Hall and Zoom: https://unl.zoom.us/j/95280191765
“Spatial and Temporal Agnostic Deep-Learning-Based Radio Fingerprinting”
Radio fingerprinting is a technique that validates wireless devices based on their unique radio frequency (RF) signals. This method is highly feasible because RF signals carry distinct hardware variations introduced during manufacturing. The security and trustworthiness of current and future wireless networks heavily rely on radio fingerprinting. In addition to identifying individual devices, it can also differentiate mission-critical targets. Despite significant efforts in the literature, existing radio fingerprinting methods require improved robustness, scalability, and resilience. This study focuses on the challenges posed by spatial-temporal variations in the wireless environment. Many prior approaches overlook the complex numerical structure of the in-phase and quadrature (I/Q) data by treating real and imaginary components separately. This approach results in the loss of essential information encoded in the signal’s phase and amplitude, leading to lower accuracy. Our paper proposes several enhancements. First, we conduct extensive experiments to determine optimal pre-processing parameters, ensuring that over-optimistic conclusions about RF fingerprinting performance are avoided. Second, we treat the entire complex structure of the I/Q data as a single input to a complex-valued convolutional neural network (CVNN), thereby improving the model’s accuracy. Third, we compare transfer learning-based fine-tuning and a triplet network to address the variations introduced by the wireless environment in scenarios involving different locations and periods. We use the concept of a “device rank” metric to perform device identification with certainty based on RF fingerprinting. Furthermore, we evaluated that the Concatenated Rectified Linear Units (CReLU) activation function outperforms two other activation functions when testing cross-location and time device fingerprints.
Committee members:
Dr. Nirnimesh Ghose, Chair
Dr. Lisong Xu
Dr. Byrav Ramamurthy
Thursday, July 27, 2023
3:00 PM
347 Avery Hall and Zoom: https://unl.zoom.us/j/95280191765
“Spatial and Temporal Agnostic Deep-Learning-Based Radio Fingerprinting”
Radio fingerprinting is a technique that validates wireless devices based on their unique radio frequency (RF) signals. This method is highly feasible because RF signals carry distinct hardware variations introduced during manufacturing. The security and trustworthiness of current and future wireless networks heavily rely on radio fingerprinting. In addition to identifying individual devices, it can also differentiate mission-critical targets. Despite significant efforts in the literature, existing radio fingerprinting methods require improved robustness, scalability, and resilience. This study focuses on the challenges posed by spatial-temporal variations in the wireless environment. Many prior approaches overlook the complex numerical structure of the in-phase and quadrature (I/Q) data by treating real and imaginary components separately. This approach results in the loss of essential information encoded in the signal’s phase and amplitude, leading to lower accuracy. Our paper proposes several enhancements. First, we conduct extensive experiments to determine optimal pre-processing parameters, ensuring that over-optimistic conclusions about RF fingerprinting performance are avoided. Second, we treat the entire complex structure of the I/Q data as a single input to a complex-valued convolutional neural network (CVNN), thereby improving the model’s accuracy. Third, we compare transfer learning-based fine-tuning and a triplet network to address the variations introduced by the wireless environment in scenarios involving different locations and periods. We use the concept of a “device rank” metric to perform device identification with certainty based on RF fingerprinting. Furthermore, we evaluated that the Concatenated Rectified Linear Units (CReLU) activation function outperforms two other activation functions when testing cross-location and time device fingerprints.
Committee members:
Dr. Nirnimesh Ghose, Chair
Dr. Lisong Xu
Dr. Byrav Ramamurthy