Dataset with Adversarial Attack on Deep Learning for Modulation Classification

This dataset contains adversarial attacks on Deep Learning (DL) when it is employed for the classification ofwireless modulated communication signals. The attack is executed with an obfuscating waveform that is embedded in thetransmitted signal in such a way that prevents the extraction of clean data for training from a wireless eavesdropper. At thesame time it allows a legitimate receiver (LRx) to demodulate the data. The scheme works for both single carrier and multi-carrierorthogonal frequency division multiplexing (OFDM) waveforms and can be implemented as part of frame-based wireless protocols.The related paper that we ask to be cited is by D. Varkatzas and A. Argyriou that appears in IEEE MILCOM 2023.