# SMILENet: Unleashing Extra-Large Capacity Image Steganography via a Synergistic Mosaic InvertibLE Hiding Network

arXiv: https://arxiv.org/abs/2503.05118 · HTML: https://mlsanity.com/paper/2503.05118/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 57 references that are in the map.
- First posted on arXiv 7 Mar 2025.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [NICE: Non-linear Independent Components Estimation](https://mlsanity.com/paper/1410.8516/) (2014)
- [HiDDeN: Hiding Data With Deep Networks](https://mlsanity.com/paper/1807.09937/) (2018)
- [The Reversible Residual Network: Backpropagation Without Storing Activations](https://mlsanity.com/paper/1707.04585/) (2017)
- [Guided Image Generation with Conditional Invertible Neural Networks](https://mlsanity.com/paper/1907.02392/) (2019)
- [i-RevNet: Deep Invertible Networks](https://mlsanity.com/paper/1802.07088/) (2018)
- [Invertible Denoising Network: A Light Solution for Real Noise Removal](https://mlsanity.com/paper/2104.10546/) (2021)
- [WINNet: Wavelet-inspired Invertible Network for Image Denoising](https://mlsanity.com/paper/2109.06381/) (2021)
- [CNN Based Adversarial Embedding with Minimum Alteration for Image Steganography](https://mlsanity.com/paper/1803.09043/) (2018)
- [Large-capacity and Flexible Video Steganography via Invertible Neural Network](https://mlsanity.com/paper/2304.12300/) (2023)
- [End-to-end Trained CNN Encode-Decoder Networks for Image Steganography](https://mlsanity.com/paper/1711.07201/) (2017)
- [Invertible Rescaling Network and Its Extensions](https://mlsanity.com/paper/2210.04188/) (2022)
- [IICNet: A Generic Framework for Reversible Image Conversion](https://mlsanity.com/paper/2109.04242/) (2021)
- [Imperceptible Adversarial Attack via Invertible Neural Networks](https://mlsanity.com/paper/2211.15030/) (2022)
- [Video Rescaling Networks with Joint Optimization Strategies for Downscaling and Upscaling](https://mlsanity.com/paper/2103.14858/) (2021)
- [LINN: Lifting Inspired Invertible Neural Network for Image Denoising](https://mlsanity.com/paper/2105.03303/) (2021)
- [Hiding Images in Deep Probabilistic Models](https://mlsanity.com/paper/2210.02257/) (2022)
- [Enhancing Image Rescaling using Dual Latent Variables in Invertible Neural Network](https://mlsanity.com/paper/2207.11844/) (2022)
- [Multi-Image Steganography Using Deep Neural Networks](https://mlsanity.com/paper/2101.00350/) (2021)
- [Invertible Mosaic Image Hiding Network for Very Large Capacity Image Steganography](https://mlsanity.com/paper/2309.08987/) (2023)

## Built on by (most cited first, 1 of 1)

- [IDATA: Scalable Invertible Diffusion for Unrestricted Adversarial Transfer Attack](https://mlsanity.com/paper/2608.08734/) (2026)

## Abstract (arXiv)

Existing image steganography methods face fundamental limitations in hiding capacity (typically 1~7 images) due to severe information interference and uncoordinated capacity-distortion trade-off. We propose SMILENet, a novel synergistic framework that achieves 25 image hiding through three key innovations: (i) A synergistic network architecture coordinates reversible and non-reversible operations to efficiently exploit information redundancy in both secret and cover images. The reversible Invertible Cover-Driven Mosaic (ICDM) module and Invertible Mosaic Secret Embedding (IMSE) module establish cover-guided mosaic transformations and representation embedding with mathematically guaranteed invertibility for distortion-free embedding. The non-reversible Secret Information Selection (SIS) module and Secret Detail Enhancement (SDE) module implement learnable feature modulation for critical information selection and enhancement. (ii) A unified training strategy that coordinates complementary modules to achieve 3.0x higher capacity than existing methods with superior visual quality. (iii) Last but not least, we introduce a new metric to model Capacity-Distortion Trade-off for evaluating the image steganography algorithms that jointly considers hiding capacity and distortion, and provides a unified evaluation approach for accessing results with different number of secret image. Extensive experiments on DIV2K, Paris StreetView and ImageNet1K show that SMILENet outperforms state-of-the-art methods in terms of hiding capacity, recovery quality as well as security against steganalysis methods.