# Learning Iterative Neural Optimizers for Image Steganography

arXiv: https://arxiv.org/abs/2303.16206 · HTML: https://mlsanity.com/paper/2303.16206/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 66 references that are in the map.
- First posted on arXiv 27 Mar 2023.

## Builds on (most cited first, 24 of 24)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples](https://mlsanity.com/paper/1802.00420/) (2018)
- [OptNet: Differentiable Optimization as a Layer in Neural Networks](https://mlsanity.com/paper/1703.00443/) (2017)
- [Differentiable Convex Optimization Layers](https://mlsanity.com/paper/1910.12430/) (2019)
- [HiDDeN: Hiding Data With Deep Networks](https://mlsanity.com/paper/1807.09937/) (2018)
- [Generative Visual Manipulation on the Natural Image Manifold](https://mlsanity.com/paper/1609.03552/) (2016)
- [StegaStamp: Invisible Hyperlinks in Physical Photographs](https://mlsanity.com/paper/1904.05343/) (2019)
- [DeepView: View Synthesis with Learned Gradient Descent](https://mlsanity.com/paper/1906.07316/) (2019)
- [Learned Primal-dual Reconstruction](https://mlsanity.com/paper/1707.06474/) (2017)
- [ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement](https://mlsanity.com/paper/2104.02699/) (2021)
- [SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solver](https://mlsanity.com/paper/1905.12149/) (2019)
- [Deep Feature Interpolation for Image Content Changes](https://mlsanity.com/paper/1611.05507/) (2016)
- [SteganoGAN: High Capacity Image Steganography with GANs](https://mlsanity.com/paper/1901.03892/) (2019)
- [Generating Steganographic Images via Adversarial Training](https://mlsanity.com/paper/1703.00371/) (2017)
- [StegExpose - A Tool for Detecting LSB Steganography](https://mlsanity.com/paper/1410.6656/) (2014)
- [Invisible Steganography via Generative Adversarial Networks](https://mlsanity.com/paper/1807.08571/) (2018)
- [End-to-end Trained CNN Encode-Decoder Networks for Image Steganography](https://mlsanity.com/paper/1711.07201/) (2017)
- [A Novel Convolutional Neural Network for Image Steganalysis with Shared Normalization](https://mlsanity.com/paper/1711.07306/) (2017)

## Built on by (most cited first, 4 of 4)

- [Watermark Anything with Localized Messages](https://mlsanity.com/paper/2411.07231/) (2024)
- [Diffusion-Stego: Training-free Diffusion Generative Steganography via Message Projection](https://mlsanity.com/paper/2305.18726/) (2023)
- [Effective Message Hiding with Order-Preserving Mechanisms](https://mlsanity.com/paper/2402.19160/) (2024)
- [Neural Cover Selection for Image Steganography](https://mlsanity.com/paper/2410.18216/) (2024)

## Abstract (arXiv)

Image steganography is the process of concealing secret information in images through imperceptible changes. Recent work has formulated this task as a classic constrained optimization problem. In this paper, we argue that image steganography is inherently performed on the (elusive) manifold of natural images, and propose an iterative neural network trained to perform the optimization steps. In contrast to classical optimization methods like L-BFGS or projected gradient descent, we train the neural network to also stay close to the manifold of natural images throughout the optimization. We show that our learned neural optimization is faster and more reliable than classical optimization approaches. In comparison to previous state-of-the-art encoder-decoder-based steganography methods, it reduces the recovery error rate by multiple orders of magnitude and achieves zero error up to 3 bits per pixel (bpp) without the need for error-correcting codes.