# Generating Steganographic Images via Adversarial Training

arXiv: https://arxiv.org/abs/1703.00371 · HTML: https://mlsanity.com/paper/1703.00371/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Mar 2017.

## Built on by (most cited first, 30 of 58)

- [Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust](https://mlsanity.com/paper/2305.20030/) (2023)
- [WAVES: Benchmarking the Robustness of Image Watermarks](https://mlsanity.com/paper/2401.08573/) (2024)
- [Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Models](https://mlsanity.com/paper/2311.04378/) (2023)
- [AI-Generated Content (AIGC): A Survey](https://mlsanity.com/paper/2304.06632/) (2023)
- [Copyright Protection in Generative AI: A Technical Perspective](https://mlsanity.com/paper/2402.02333/) (2024)
- [Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directions](https://mlsanity.com/paper/2303.02213/) (2023)
- [StegaNeRF: Embedding Invisible Information within Neural Radiance Fields](https://mlsanity.com/paper/2212.01602/) (2022)
- [SynthID-Image: Image watermarking at internet scale](https://mlsanity.com/paper/2510.09263/) (2025)
- [Generative Watermarking Against Unauthorized Subject-Driven Image Synthesis](https://mlsanity.com/paper/2306.07754/) (2023)
- [Large-capacity and Flexible Video Steganography via Invertible Neural Network](https://mlsanity.com/paper/2304.12300/) (2023)
- [Learning to Immunize Images for Tamper Localization and Self-Recovery](https://mlsanity.com/paper/2210.15902/) (2022)
- [Universal Adversarial Perturbations Through the Lens of Deep Steganography: Towards A Fourier Perspective](https://mlsanity.com/paper/2102.06479/) (2021)
- [FaceSigns: Semi-Fragile Neural Watermarks for Media Authentication and Countering Deepfakes](https://mlsanity.com/paper/2204.01960/) (2022)
- [Watermarking Language Models for Many Adaptive Users](https://mlsanity.com/paper/2405.11109/) (2024)
- [Generative Steganography Network](https://mlsanity.com/paper/2207.13867/) (2022)
- [On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlook](https://mlsanity.com/paper/2307.16680/) (2023)
- [SoK: On the Role and Future of AIGC Watermarking in the Era of Gen-AI](https://mlsanity.com/paper/2411.11478/) (2024)
- [From Image to Imuge: Immunized Image Generation](https://mlsanity.com/paper/2110.14196/) (2021)
- [GaussianStego: A Generalizable Stenography Pipeline for Generative 3D Gaussians Splatting](https://mlsanity.com/paper/2407.01301/) (2024)
- [Embedding Novel Views in a Single JPEG Image](https://mlsanity.com/paper/2108.13003/) (2021)
- [Purified and Unified Steganographic Network](https://mlsanity.com/paper/2402.17210/) (2024)
- [A Brief Survey on Deep Learning Based Data Hiding](https://mlsanity.com/paper/2103.01607/) (2021)
- [RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guarantees](https://mlsanity.com/paper/2403.18774/) (2024)
- [U Can't Gen This? A Survey of Intellectual Property Protection Methods for Data in Generative AI](https://mlsanity.com/paper/2406.15386/) (2024)
- [Multi-Stage Residual Hiding for Image-into-Audio Steganography](https://mlsanity.com/paper/2101.01872/) (2021)
- [Social Media Authentication and Combating Deepfakes using Semi-fragile Invisible Image Watermarking](https://mlsanity.com/paper/2410.01906/) (2024)
- [PRIS: Practical robust invertible network for image steganography](https://mlsanity.com/paper/2309.13620/) (2023)
- [Learning Iterative Neural Optimizers for Image Steganography](https://mlsanity.com/paper/2303.16206/) (2023)
- [DeepFormableTag: End-to-end Generation and Recognition of Deformable Fiducial Markers](https://mlsanity.com/paper/2206.08026/) (2022)
- [Low-frequency Image Deep Steganography: Manipulate the Frequency Distribution to Hide Secrets with Tenacious Robustness](https://mlsanity.com/paper/2303.13713/) (2023)

## Abstract (arXiv)

Adversarial training was recently shown to be competitive against supervised learning methods on computer vision tasks, however, studies have mainly been confined to generative tasks such as image synthesis. In this paper, we apply adversarial training techniques to the discriminative task of learning a steganographic algorithm. Steganography is a collection of techniques for concealing information by embedding it within a non-secret medium, such as cover texts or images. We show that adversarial training can produce robust steganographic techniques: our unsupervised training scheme produces a steganographic algorithm that competes with state-of-the-art steganographic techniques, and produces a robust steganalyzer, which performs the discriminative task of deciding if an image contains secret information. We define a game between three parties, Alice, Bob and Eve, in order to simultaneously train both a steganographic algorithm and a steganalyzer. Alice and Bob attempt to communicate a secret message contained within an image, while Eve eavesdrops on their conversation and attempts to determine if secret information is embedded within the image. We represent Alice, Bob and Eve by neural networks, and validate our scheme on two independent image datasets, showing our novel method of studying steganographic problems is surprisingly competitive against established steganographic techniques.