Radio frequency fingerprint (RFF) has attracted a remarkable surge of attention to wireless transmitter identification due to the inimitable hardware imperfection. However, most RFF-based schemes devised in controlled environments are unable to reach the claimed performance in real-world scenarios. This paper proposes a practical RFF identification method for mobile phones in Global System for Mobile (GSM) system. Specifically, the instantaneous amplitude of near-transient part in normal burst (NB) is regarded as RFF that extracted from up-link communications. In addition, an anomaly filtering and stacking (AFS) method is introduced to obtain stable RFF in Time Division Multiple Access (TDMA) system. Lastly, the impacts of frequency point and sending power variations on RFF are fully dissected in comparison experiments. Experiments on 10 mobile phones show that the proposed RFF scheme yields 99.17% True Acceptance Rate (TAR) in real wireless environments. Experiments also show that the varying transmission power decreases the accuracy of RFF identification.

由于无法模仿的硬件缺陷，射频指纹（RFF）引起了对无线发射机识别的极大关注。然而，在受控环境中设计的大多数基于 RFF 的方案都无法在实际场景中达到声称的性能。本文提出了一种实用的全球移动通信系统（GSM）系统中手机的RFF识别方法。具体而言，将正常突发（NB）中近瞬态部分的瞬时幅度视为从上行链路通信中提取的RFF。此外，为了在时分多址（TDMA）系统中获得稳定的RFF，引入了异常过滤和堆叠（AFS）方法。最后，在对比实验中充分剖析了频点和发送功率变化对RFF的影响。在 10 部手机上进行的实验表明，所提出的 RFF 方案在真实无线环境中产生了 99.17% 的真实接受率（TAR）。实验还表明，不同的发射功率会降低RFF识别的准确性。