# Pixel-Stega: Generative Image Steganography Based on Autoregressive Models

arXiv: https://arxiv.org/abs/2112.10945 · HTML: https://mlsanity.com/paper/2112.10945/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 55 references that are in the map.
- First posted on arXiv 21 Dec 2021.

## Builds on (most cited first, 7 of 7)

- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications](https://mlsanity.com/paper/1701.05517/) (2017)
- [Neural Linguistic Steganography](https://mlsanity.com/paper/1909.01496/) (2019)
- [Provably Secure Generative Linguistic Steganography](https://mlsanity.com/paper/2106.02011/) (2021)
- [CNN Based Adversarial Embedding with Minimum Alteration for Image Steganography](https://mlsanity.com/paper/1803.09043/) (2018)
- [Yedrouj-Net: An efficient CNN for spatial steganalysis](https://mlsanity.com/paper/1803.00407/) (2018)
- [Coverless Information Hiding Based on Generative adversarial networks](https://mlsanity.com/paper/1712.06951/) (2017)

## Abstract (arXiv)

In this letter, we explored generative image steganography based on autoregressive models. We proposed Pixel-Stega, which implements pixel-level information hiding with autoregressive models and arithmetic coding algorithm. Firstly, one of the autoregressive models, PixelCNN++, is utilized to produce explicit conditional probability distribution of each pixel. Secondly, secret messages are encoded to the selection of pixels through steganographic sampling (stegosampling) based on arithmetic coding. We carried out qualitative and quantitative assessment on gray-scale and colour image datasets. Experimental results show that Pixel-Stega is able to embed secret messages adaptively according to the entropy of the pixels to achieve both high embedding capacity (up to 4.3 bpp) and nearly perfect imperceptibility (about 50% detection accuracy).