TY - GEN
T1 - On the Domain Generalizability of RF Fingerprints Through Multifractal Dimension Representation
AU - Johnson, Benjamin
AU - Hamdaoui, Bechir
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - RF data-driven device fingerprinting through the use of deep learning has recently surfaced as a possible method for enabling secure device identification and authentication. Traditional approaches are commonly susceptible to the domain adaptation problem where a model trained on data collected under one domain performs badly when tested on data collected under a different domain. Some examples of a domain change include varying the location or environment of the device and varying the time or day of the data collection. In this work, we propose using multifractal analysis and the variance fractal dimension trajectory (VFDT) as a data representation input to the deep neural network to extract device fingerprints that are domain generalizable. We analyze the effectiveness of the proposed VFDT representation in detecting device-specific signatures from hardware-impaired IQ (in-phase and quadrature) signals, and we evaluate its robustness in real-world settings, using an experimental testbed of 30 WiFi-enabled Pycom devices. Our experimental results show that the proposed VFDT representation improves the scalability, robustness and generalizability of the deep learning models significantly compared to when using IQ data samples.
AB - RF data-driven device fingerprinting through the use of deep learning has recently surfaced as a possible method for enabling secure device identification and authentication. Traditional approaches are commonly susceptible to the domain adaptation problem where a model trained on data collected under one domain performs badly when tested on data collected under a different domain. Some examples of a domain change include varying the location or environment of the device and varying the time or day of the data collection. In this work, we propose using multifractal analysis and the variance fractal dimension trajectory (VFDT) as a data representation input to the deep neural network to extract device fingerprints that are domain generalizable. We analyze the effectiveness of the proposed VFDT representation in detecting device-specific signatures from hardware-impaired IQ (in-phase and quadrature) signals, and we evaluate its robustness in real-world settings, using an experimental testbed of 30 WiFi-enabled Pycom devices. Our experimental results show that the proposed VFDT representation improves the scalability, robustness and generalizability of the deep learning models significantly compared to when using IQ data samples.
KW - Device fingerprinting
KW - deep learning
KW - device authentication
KW - domain generalizability
KW - hardware impairments
KW - multifractal analysis
KW - variance fractal dimension trajectory.
UR - https://www.scopus.com/pages/publications/85177591029
U2 - 10.1109/CNS59707.2023.10289056
DO - 10.1109/CNS59707.2023.10289056
M3 - Conference contribution
AN - SCOPUS:85177591029
T3 - 2023 IEEE Conference on Communications and Network Security, CNS 2023
BT - 2023 IEEE Conference on Communications and Network Security, CNS 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2023 IEEE Conference on Communications and Network Security, CNS 2023
Y2 - 2 October 2023 through 5 October 2023
ER -