As new technologies spread, phone fraud crimes have become master strategies to steal money and personal identities. Inspired by website authentication, we propose an end-to-end data modem over voice channels that can transmit the caller’s digital certificate to the callee for verification. Without assistance from telephony providers, it is difficult to carry useful information over voice channels. For example, voice activity detection may quickly classify the encoded signals as nonspeech signals and reject the input waveform. To address this problem, we propose a chirp-based modulation method and corresponding demodulator using deep learning technology. We demonstrate that FastDOV works in the real world and outperforms the existing methods in terms of goodput.
The contributions of this work are summarized as follows:
• We propose a novel chirp-based modulation scheme and a DL-based demodulation scheme robust to distortions and interruption in ordinary cellular voice
channels.
• We design a dedicated data link protocol for our modulation/demodulation schemes to synchronize the data communication and provide retransmission support.
• We present a working prototype of FastDOV and extensive empirical study under various environmental factors. The evaluation results show that FastDOV achieves higher goodput than state-of-the-art approaches