PIXINWAV: RESIDUAL STEGANOGRAPHY FOR HIDING PIXELS IN AUDIO

Steganography comprises the mechanics of hiding data in a host media that may be publicly available. While previous works focused onunimodal setups (e.g., hiding images in images, or hiding audio in audio), PixInWav targets the multimodal case of hiding images in audio.To this end, we propose a novel residual architecture operating on topof short-time discrete cosine transform (STDCT) audio spectrograms.Among our results, we find that the residual steganography setup wepropose allows an encoding of the hidden image that is independentfrom the host audio without compromising quality. Accordingly,while previous works require both host and hidden signals to hidea signal, PixInWav can encode images offline?which can be laterhidden, in a residual fashion, into any audio signal