Pixel-Stega: Generative Image Steganography Based on Autoregressive Models
This addresses the need for secure and efficient image steganography, offering a novel approach that improves upon existing methods in terms of capacity and stealth, though it is incremental in combining autoregressive models with steganography.
The authors tackled the problem of hiding secret messages in images by proposing Pixel-Stega, a method using autoregressive models and arithmetic coding to embed messages at the pixel level, achieving high embedding capacity up to 4.3 bpp and nearly perfect imperceptibility with about 50% detection accuracy.
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).