# Deep Cross-Modal Steganography Using Neural Representations

arXiv: https://arxiv.org/abs/2307.08671 · HTML: https://mlsanity.com/paper/2307.08671/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 20 references that are in the map.
- First posted on arXiv 2 Jul 2023.

## Builds on (most cited first, 6 of 6)

- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Implicit Geometric Regularization for Learning Shapes](https://mlsanity.com/paper/2002.10099/) (2020)
- [HiDDeN: Hiding Data With Deep Networks](https://mlsanity.com/paper/1807.09937/) (2018)
- [StegaStamp: Invisible Hyperlinks in Physical Photographs](https://mlsanity.com/paper/1904.05343/) (2019)
- [Generating Steganographic Images via Adversarial Training](https://mlsanity.com/paper/1703.00371/) (2017)

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

- [Implicit Steganography Beyond the Constraints of Modality](https://mlsanity.com/paper/2312.05496/) (2023)
- [StegaINR4MIH: steganography by implicit neural representation for multi-image hiding](https://mlsanity.com/paper/2410.10117/) (2024)

## Abstract (arXiv)

Steganography is the process of embedding secret data into another message or data, in such a way that it is not easily noticeable. With the advancement of deep learning, Deep Neural Networks (DNNs) have recently been utilized in steganography. However, existing deep steganography techniques are limited in scope, as they focus on specific data types and are not effective for cross-modal steganography. Therefore, We propose a deep cross-modal steganography framework using Implicit Neural Representations (INRs) to hide secret data of various formats in cover images. The proposed framework employs INRs to represent the secret data, which can handle data of various modalities and resolutions. Experiments on various secret datasets of diverse types demonstrate that the proposed approach is expandable and capable of accommodating different modalities.