# Generative Steganographic Flow

arXiv: https://arxiv.org/abs/2305.05838 · HTML: https://mlsanity.com/paper/2305.05838/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 17 references that are in the map.
- First posted on arXiv 10 May 2023.

## Builds on (most cited first, 3 of 3)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)

## Built on by (most cited first, 7 of 7)

- [Diffusion-Stego: Training-free Diffusion Generative Steganography via Message Projection](https://mlsanity.com/paper/2305.18726/) (2023)
- [Plug-and-Hide: Provable and Adjustable Diffusion Generative Steganography](https://mlsanity.com/paper/2409.04878/) (2024)
- [Double-Flow-based Steganography without Embedding for Image-to-Image Hiding](https://mlsanity.com/paper/2311.15027/) (2023)
- [Approximate Gaussian Mapping for Generative Image Steganography](https://mlsanity.com/paper/2510.07219/) (2025)
- [Training-Free Color-Aware Adversarial Diffusion Sanitization for Diffusion Stegomalware Defense at Security Gateways](https://mlsanity.com/paper/2512.24499/) (2025)
- [Rethinking Security of Diffusion-based Generative Steganography](https://mlsanity.com/paper/2602.10219/) (2026)
- [No Prompt, No Leaks: A Robust Generative Steganography Framework via Prompt-Free Diffusion](https://mlsanity.com/paper/2606.31427/) (2026)

## Abstract (arXiv)

Generative steganography (GS) is a new data hiding manner, featuring direct generation of stego media from secret data. Existing GS methods are generally criticized for their poor performances. In this paper, we propose a novel flow based GS approach -- Generative Steganographic Flow (GSF), which provides direct generation of stego images without cover image. We take the stego image generation and secret data recovery process as an invertible transformation, and build a reversible bijective mapping between input secret data and generated stego images. In the forward mapping, secret data is hidden in the input latent of Glow model to generate stego images. By reversing the mapping, hidden data can be extracted exactly from generated stego images. Furthermore, we propose a novel latent optimization strategy to improve the fidelity of stego images. Experimental results show our proposed GSF has far better performances than SOTA works.