Radio frequency fingerprint identification (RFFI) is an emerging technique for the lightweight authentication of wireless Internet of things (IoT) devices. RFFI exploits unique hardware impairments as device identifiers, and deep learning is widely deployed as the feature extractor and classifier for RFFI. However, deep learning is vulnerable to adversarial attacks, where adversarial examples are generated by adding perturbation to clean data for causing the classifier to make wrong predictions. Deep learning-based RFFI has been shown to be vulnerable to such attacks, however, there is currently no exploration of effective adversarial attacks against a diversity of RFFI classifiers. In this paper, we report on investigations into white-box attacks (non-targeted and targeted) using two approaches, namely the fast gradient sign method (FGSM) and projected gradient descent (PGD). A LoRa testbed was built and real datasets were collected. These adversarial examples have been experimentally demonstrated to be effective against convolutional neural networks (CNNs), long short-term memory (LSTM) networks, and gated recurrent units (GRU).

翻译：射频指纹识别（RFFI）是一种新兴的无线物联网（IoT）设备轻量级认证技术。RFFI利用独特的硬件缺陷作为设备标识符，而深度学习被广泛用作RFFI的特征提取器和分类器。然而，深度学习容易受到对抗性攻击，即通过向干净数据添加扰动生成对抗样本，导致分类器做出错误预测。基于深度学习的RFFI已被证明容易受到此类攻击，但目前尚未有研究探索针对多种RFFI分类器的有效对抗攻击。本文报告了使用快速梯度符号法（FGSM）和投影梯度下降法（PGD）两种方法进行的白盒攻击（非定向与定向）研究。我们搭建了LoRa测试平台并采集了真实数据集。实验证明，这些对抗样本对卷积神经网络（CNN）、长短期记忆（LSTM）网络和门控循环单元（GRU）均具有有效性。