Research map / Image generation / Autoregressive and latent generation
RFNNS: Robust Fixed Neural Network Steganography with Universal Text-to-Image Models
Yu Cheng, Jiuan Zhou, Jiawei Chen, Zhaoxia Yin, Xinpeng Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 RFNNS instead of Li et al. under contrast attack | FNNS · Recovered secret, 1.5 bpp Contrast 0.7 | PSNR: 13.86 -> 33.68 | Improved |
| use RFNNS instead of Li et al. under Gaussian noise | FNNS · Stego image, 6 bpp Gaussian noise 0.07 | PSNR: 19.88 -> 26.19 | Improved |
| use RFNNS instead of Li et al. without attack, 6 bpp | FNNS · Recovered secret, 6 bpp No Attack | PSNR: 34.61 -> 31.09 | Hurt |
| use RFNNS instead of Li et al. without attack, 1.5 bpp | FNNS · Recovered secret, 1.5 bpp No Attack | PSNR: 35.34 -> 34.14 | No clear effect |
| add robust perturbation generation (RSPG) with simulated attacks | FNNS · Unknown attack Type2 6bpp | PSNR: 16.25 -> 28.00 | Improved |
| add texture-aware localization of perturbation regions | FNNS · Stego image, 1.5 bpp No Attack | PSNR: 41.17 -> 41.48 | No clear effect |
| add texture-aware localization and RSPG | FNNS · anti-steganalysis (StegExpose) | ROC detectability | Improved |
Closest papers by meaning
- Robust Message Embedding via Attention Flow-Based Steganography (CVPR 2025 · similarity 0.88)
- Provably Secure Image Robust Steganography via Cross-modal Error Correction (AAAI 2025 · similarity 0.88)
- Neural Cover Selection for Image Steganography (NeurIPS 2024 · similarity 0.87)
- SSHR: More Secure Generative Steganography with High-Quality Revealed Secret Images (ICML 2025 · similarity 0.86)
- StegoGAN: Leveraging Steganography for Non-Bijective Image-to-Image Translation (CVPR 2024 · similarity 0.86)
- StegaStyleGAN: Towards Generic and Practical Generative Image Steganography (AAAI 2024 · similarity 0.86)
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.
