Vanessa Chen , Jiachen Xu , Yuyi Shen , and Ethan Chen RF Fingerprint Classification With CombinatorialRandomness-Based Power Amplifiers and Convolutional Neural Networks Secure analog/ RF electronics and electromagnetics T 28 he growth of the IoT requires more comprehensive security measures than ever. RF fingerprinting (RFF) utilizes features in the signals and waveDigital Object Identifier 10.1109/MSSC.2022.3200302 Date of current version: 11 November 2022 forms from transmitters' physical-layer imperfections to classify and authenticate devices. To prevent attacks from impersonators, combinatorial randomness is exploited to augment the RF fingerprints with a high-efficiency PA for IoT applications. By enabling different subsets of thinly sliced PA elements, the transmitter FALL 2022 IEEE SOLID-STATE CIRCUITS MAGAZINE can be reconfigured with 220 subsets that exhibit distinctive RF fingerprints for signal analysis at the edge. In this work, a combinatorial-randomnessbased PA was implemented in a BLE system. The BLE packets' in-phase and quadrature samples transmitted from each configuration are collected with different SNRs to emulate the 1943-0582/22©2022IEEE TOP FIGURE:HTTPS://WWW.ECE.CMU.EDU/NEWS-AND-EVENTS/STORY/2022/02/FINGERPRINTING-THE-IOT.HTMLhttps://orcid.org/0000-0002-9792-5397 https://orcid.org/0000-0001-9798-7419 https://orcid.org/0000-0001-9532-3395 https://orcid.org/0000-0003-4190-6370