# Towards Robust Image-in-Audio Deep Steganography

arXiv: https://arxiv.org/abs/2303.05007 · HTML: https://mlsanity.com/paper/2303.05007/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 45 references that are in the map.
- First posted on arXiv 9 Mar 2023.

## Builds on (most cited first, 10 of 10)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [HiDDeN: Hiding Data With Deep Networks](https://mlsanity.com/paper/1807.09937/) (2018)
- [Soft-DTW: a Differentiable Loss Function for Time-Series](https://mlsanity.com/paper/1703.01541/) (2017)
- [Learning Sound Event Classifiers from Web Audio with Noisy Labels](https://mlsanity.com/paper/1901.01189/) (2019)
- [End-to-end Trained CNN Encode-Decoder Networks for Image Steganography](https://mlsanity.com/paper/1711.07201/) (2017)
- [StegNet: Mega Image Steganography Capacity with Deep Convolutional Network](https://mlsanity.com/paper/1806.06357/) (2018)
- [Hide and Speak: Towards Deep Neural Networks for Speech Steganography](https://mlsanity.com/paper/1902.03083/) (2019)
- [PixInWav: Residual Steganography for Hiding Pixels in Audio](https://mlsanity.com/paper/2106.09814/) (2021)

## Built on by (most cited first, 2 of 2)

- [WavMark: Watermarking for Audio Generation](https://mlsanity.com/paper/2308.12770/) (2023)
- [WavInWav: Time-domain Speech Hiding via Invertible Neural Network](https://mlsanity.com/paper/2510.02915/) (2025)

## Abstract (arXiv)

The field of steganography has experienced a surge of interest due to the recent advancements in AI-powered techniques, particularly in the context of multimodal setups that enable the concealment of signals within signals of a different nature. The primary objectives of all steganographic methods are to achieve perceptual transparency, robustness, and large embedding capacity - which often present conflicting goals that classical methods have struggled to reconcile. This paper extends and enhances an existing image-in-audio deep steganography method by focusing on improving its robustness. The proposed enhancements include modifications to the loss function, utilization of the Short-Time Fourier Transform (STFT), introduction of redundancy in the encoding process for error correction, and buffering of additional information in the pixel subconvolution operation. The results demonstrate that our approach outperforms the existing method in terms of robustness and perceptual transparency.