# Natias: Neuron Attribution based Transferable Image Adversarial Steganography

arXiv: https://arxiv.org/abs/2409.04968 · HTML: https://mlsanity.com/paper/2409.04968/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 76 references that are in the map.
- First posted on arXiv 8 Sep 2024.

## Builds on (most cited first, 11 of 11)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Countering Adversarial Images using Input Transformations](https://mlsanity.com/paper/1711.00117/) (2017)
- [Defense against Adversarial Attacks Using High-Level Representation Guided Denoiser](https://mlsanity.com/paper/1712.02976/) (2017)
- [CNN Features off-the-shelf: an Astounding Baseline for Recognition](https://mlsanity.com/paper/1403.6382/) (2014)
- [Regularizing deep networks using efficient layerwise adversarial training](https://mlsanity.com/paper/1705.07819/) (2017)
- [CNN Based Adversarial Embedding with Minimum Alteration for Image Steganography](https://mlsanity.com/paper/1803.09043/) (2018)
- [WISERNet: Wider Separate-then-reunion Network for Steganalysis of Color Images](https://mlsanity.com/paper/1803.04805/) (2018)
- [CALPA-NET: Channel-pruning-assisted Deep Residual Network for Steganalysis of Digital Images](https://mlsanity.com/paper/1911.04657/) (2019)
- [Enhancing JPEG Steganography using Iterative Adversarial Examples](https://mlsanity.com/paper/1909.07556/) (2019)

## Abstract (arXiv)

Image steganography is a technique to conceal secret messages within digital images. Steganalysis, on the contrary, aims to detect the presence of secret messages within images. Recently, deep-learning-based steganalysis methods have achieved excellent detection performance. As a countermeasure, adversarial steganography has garnered considerable attention due to its ability to effectively deceive deep-learning-based steganalysis. However, steganalysts often employ unknown steganalytic models for detection. Therefore, the ability of adversarial steganography to deceive non-target steganalytic models, known as transferability, becomes especially important. Nevertheless, existing adversarial steganographic methods do not consider how to enhance transferability. To address this issue, we propose a novel adversarial steganographic scheme named Natias. Specifically, we first attribute the output of a steganalytic model to each neuron in the target middle layer to identify critical features. Next, we corrupt these critical features that may be adopted by diverse steganalytic models. Consequently, it can promote the transferability of adversarial steganography. Our proposed method can be seamlessly integrated with existing adversarial steganography frameworks. Thorough experimental analyses affirm that our proposed technique possesses improved transferability when contrasted with former approaches, and it attains heightened security in retraining scenarios.