Research map / Image generation / Image restoration
Robust Invertible Image Steganography
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use RIIS instead of ISN+ | Image steganography · Gaussian noise σ = 10 | secret PSNR: 27.12 -> 28.22 | Helped |
| Use RIIS instead of ISN+ | Image steganography · Gaussian noise σ = 1 | secret PSNR: 28.98 -> 30.32 | Helped |
| Use RIIS instead of ISN+ | Image steganography · Poisson Noise | secret PSNR: 26.71 -> 27.47 | Helped |
| Use RIIS instead of ISN+ | Image steganography · JPEG QF=40 | secret PSNR: 26.25 -> 27.32 | Helped |
| Use RIIS instead of ISN+ | Image steganography · JPEG QF=90 | secret PSNR: 27.48 -> 28.71 | Helped |
| Use RIIS instead of IICNet | Image steganography · ImageNet, 5 secret images | container PSNR: 35.64 -> 35.92 | Helped |
| Use RIIS instead of IICNet | Image steganography · ImageNet, 5 secret images | secret PSNR: 37.94 -> 38.13 | Helped |
| Use RIIS instead of HiNet | Image steganography · ImageNet, 1 secret image | container PSNR: 44.16 -> 43.97 | Hurt |
| Use RIIS instead of HiNet | Image steganography · ImageNet, 1 secret image | secret PSNR: 46.48 -> 46.71 | Helped |
| Add two-stage decoupled tuning (2DT) (ablation) | RIIS · Gaussian σ = 10 | secret PSNR: 27.61 -> 28.08 | Helped |
| Add content-aware noise projection (CANP) (ablation) | RIIS · Gaussian σ = 10 | secret PSNR: 27.38 -> 28.08 | Helped |
| Add container enhancement module (CEM) (ablation) | RIIS · Gaussian σ = 10 | secret PSNR: 27.82 -> 28.08 | Helped |
Closest papers by meaning
- Robust Message Embedding via Attention Flow-Based Steganography (CVPR 2025 · similarity 0.89)
- Provably Secure Image Robust Steganography via Cross-modal Error Correction (AAAI 2025 · similarity 0.86)
- StegFormer: Rebuilding the Glory of Autoencoder-Based Steganography (AAAI 2024 · similarity 0.84)
- Hiding Images in Diffusion Models by Editing Learned Score Functions (CVPR 2025 · similarity 0.83)
- SSHR: More Secure Generative Steganography with High-Quality Revealed Secret Images (ICML 2025 · similarity 0.83)
- StegaStyleGAN: Towards Generic and Practical Generative Image Steganography (AAAI 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.