PixInWav: Residual Steganography for Hiding Pixels in Audio

06/17/2021
by   Margarita Geleta, et al.
0

Steganography comprises the mechanics of hiding data in a host media that may be publicly available. While previous works focused on unimodal 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 top of short-time discrete cosine transform (STDCT) audio spectrograms. Among our results, we find that the residual audio steganography setup we propose allows independent encoding of the hidden image from the host audio without compromising quality. Accordingly, while previous works require both host and hidden signals to hide a signal, PixInWav can encode images offline – which can be later hidden, in a residual fashion, into any audio signal. Finally, we test our scheme in a lab setting to transmit images over airwaves from a loudspeaker to a microphone verifying our theoretical insights and obtaining promising results.

READ FULL TEXT

page 5

page 6

page 7

page 8

page 9

research
02/21/2019

A Parallel Optical Image Security System with Cascaded Phase-only Masks

In many previous works, a cascaded phase-only mask (or phase-only hologr...
research
12/08/2022

High Quality Audio Coding with MDCTNet

We propose a neural audio generative model, MDCTNet, operating in the pe...
research
04/10/2017

Robust Audio Watermarking Algorithm Based on Moving Average and DCT

Noise is often brought to host audio by common signal processing operati...
research
01/06/2021

Multi-Stage Residual Hiding for Image-into-Audio Steganography

The widespread application of audio communication technologies has speed...
research
04/01/2022

Residual-guided Personalized Speech Synthesis based on Face Image

Previous works derive personalized speech features by training the model...
research
08/19/2020

HpRNet : Incorporating Residual Noise Modeling for Violin in a Variational Parametric Synthesizer

Generative Models for Audio Synthesis have been gaining momentum in the ...
research
07/11/2023

Point to the Hidden: Exposing Speech Audio Splicing via Signal Pointer Nets

Verifying the integrity of voice recording evidence for criminal investi...

Please sign up or login with your details

Forgot password? Click here to reset