# Invisible Steganography via Generative Adversarial Networks

arXiv: https://arxiv.org/abs/1807.08571 · HTML: https://mlsanity.com/paper/1807.08571/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jul 2018.

## Built on by (most cited first, 21 of 21)

- [DiffusionShield: A Watermark for Copyright Protection against Generative Diffusion Models](https://mlsanity.com/paper/2306.04642/) (2023)
- [Copyright Protection in Generative AI: A Technical Perspective](https://mlsanity.com/paper/2402.02333/) (2024)
- [Data Hiding with Deep Learning: A Survey Unifying Digital Watermarking and Steganography](https://mlsanity.com/paper/2107.09287/) (2021)
- [Watermark-embedded Adversarial Examples for Copyright Protection against Diffusion Models](https://mlsanity.com/paper/2404.09401/) (2024)
- [FaceSigns: Semi-Fragile Neural Watermarks for Media Authentication and Countering Deepfakes](https://mlsanity.com/paper/2204.01960/) (2022)
- [On the Exploitation of Deepfake Model Recognition](https://mlsanity.com/paper/2204.04513/) (2022)
- [Semantic Deep Hiding for Robust Unlearnable Examples](https://mlsanity.com/paper/2406.17349/) (2024)
- [A Brief Survey on Deep Learning Based Data Hiding](https://mlsanity.com/paper/2103.01607/) (2021)
- [Multi-Stage Residual Hiding for Image-into-Audio Steganography](https://mlsanity.com/paper/2101.01872/) (2021)
- [Learning Iterative Neural Optimizers for Image Steganography](https://mlsanity.com/paper/2303.16206/) (2023)
- [Multitask Identity-Aware Image Steganography via Minimax Optimization](https://mlsanity.com/paper/2107.05819/) (2021)
- [FastStamp: Accelerating Neural Steganography and Digital Watermarking of Images on FPGAs](https://mlsanity.com/paper/2209.12391/) (2022)
- [Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach](https://mlsanity.com/paper/2511.19316/) (2025)
- [CLPSTNet: A Progressive Multi-Scale Convolutional Steganography Model Integrating Curriculum Learning](https://mlsanity.com/paper/2504.16364/) (2025)
- [STCL:Curriculum learning Strategies for deep learning image steganography models](https://mlsanity.com/paper/2504.17609/) (2025)
- [Deep Data Hiding for ICAO-Compliant Face Images: A Survey](https://mlsanity.com/paper/2508.19324/) (2025)
- [Position: Life-Logging Video Streams Make the Privacy-Utility Trade-off Inevitable](https://mlsanity.com/paper/2605.10404/) (2026)
- [Double-Flow-based Steganography without Embedding for Image-to-Image Hiding](https://mlsanity.com/paper/2311.15027/) (2023)
- [TSCL:Multi-party loss Balancing scheme for deep learning Image steganography based on Curriculum learning](https://mlsanity.com/paper/2504.18348/) (2025)
- [Approximate Gaussian Mapping for Generative Image Steganography](https://mlsanity.com/paper/2510.07219/) (2025)
- [Exploring AI in Steganography and Steganalysis: Trends, Clusters, and Sustainable Development Potential](https://mlsanity.com/paper/2511.12052/) (2025)

## Abstract (arXiv)

Nowadays, there are plenty of works introducing convolutional neural networks (CNNs) to the steganalysis and exceeding conventional steganalysis algorithms. These works have shown the improving potential of deep learning in information hiding domain. There are also several works based on deep learning to do image steganography, but these works still have problems in capacity, invisibility and security. In this paper, we propose a novel CNN architecture named as isgan to conceal a secret gray image into a color cover image on the sender side and exactly extract the secret image out on the receiver side. There are three contributions in our work: (i) we improve the invisibility by hiding the secret image only in the Y channel of the cover image; (ii) We introduce the generative adversarial networks to strengthen the security by minimizing the divergence between the empirical probability distributions of stego images and natural images. (iii) In order to associate with the human visual system better, we construct a mixed loss function which is more appropriate for steganography to generate more realistic stego images and reveal out more better secret images. Experiment results show that ISGAN can achieve start-of-art performances on LFW, Pascal VOC2012 and ImageNet datasets.