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.

In this paper we are interested to learn from a wireless digitally modulated signal the number of antennas that the transmitter (Tx) of this signal uses, as well as its specific modulation scheme (from phase-shift keying (PSK) or quadrature amplitude modulation (QAM)). Formally, these are modulation and antenna classification problems. We examine the problems with data-driven machine learning (ML)-based techniques. The two sub-problems of modulation and number of transmitter antenna classification are initially examined independently for a variety for system parameters, namely the SNR, number of receiver (Rx) antennas, and classification algorithms. Then we consider the joint problem where we follow two approaches. One, where the sub-problems are solved independently and in parallel, and one where the antenna classifier waits on the result of the modulation classifier. The two proposed schemes do not require any knowledge/details of the used modulation schemes and the way the Tx antennas are used (spatial multiplexing, space-time codes,etc.) as it is fully data-driven and not decision-theoretic based. The results of our approach are characterized by high classification accuracy and they pave the way for more ML-based data-driven techniques that reveal more characteristics of the Tx.