In this paper we propose a method for defending against an eavesdropper that uses a Deep Neural Network (DNN) for learning the modulation of wireless communication signals. Our method is based on manipulating the emitted waveform with the aid of a continuous time frequency-modulated (FM) obfuscating signal that is mixed with the modulated data. The resulting waveform allows a legitimate receiver (LRx) to demodulate the data but it increases the test error of a pre-trained or adversarially-trained DNN classifier at the eavesdropper. The scheme works for analog modulation and digital single carrier and multi carrier orthogonal frequency division multiplexing (OFDM) waveforms, while it can implemented in frame-based wireless protocols. The results indicate that careful selection of the parameters of the obfuscating waveform can drop classification performance at the eavesdropper to less than 10% in AWGN and fading channels with no performance loss at the LRx.

翻译：本文提出一种抵御利用深度神经网络（DNN）学习无线通信信号调制的窃听者的防御方法。该方法借助连续时间调频（FM）混淆信号与调制数据混合，对发射波形进行操控。生成的波形允许合法接收机（LRx）解调数据，但会显著提升窃听端预训练或对抗训练DNN分类器的测试误差。该方案适用于模拟调制、数字单载波及多载波正交频分复用（OFDM）波形，并可部署于基于帧的无线协议。实验结果表明，在加性白高斯噪声（AWGN）信道和衰落信道中，通过精心选择混淆波形参数，可将窃听端的分类性能降至10%以下，且对合法接收机性能无任何损失。