AI Paper Atlas

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

AAAI 2026 · Image generation › Autoregressive and latent generation · approach: Robust diffusion watermarking · 5 citations (OpenAlex)

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 changedWhereMeasuredEffect
use RFNNS instead of Li et al. under contrast attackFNNS · Recovered secret, 1.5 bpp Contrast 0.7PSNR: 13.86 -> 33.68Improved
use RFNNS instead of Li et al. under Gaussian noiseFNNS · Stego image, 6 bpp Gaussian noise 0.07PSNR: 19.88 -> 26.19Improved
use RFNNS instead of Li et al. without attack, 6 bppFNNS · Recovered secret, 6 bpp No AttackPSNR: 34.61 -> 31.09Hurt
use RFNNS instead of Li et al. without attack, 1.5 bppFNNS · Recovered secret, 1.5 bpp No AttackPSNR: 35.34 -> 34.14No clear effect
add robust perturbation generation (RSPG) with simulated attacksFNNS · Unknown attack Type2 6bppPSNR: 16.25 -> 28.00Improved
add texture-aware localization of perturbation regionsFNNS · Stego image, 1.5 bpp No AttackPSNR: 41.17 -> 41.48No clear effect
add texture-aware localization and RSPGFNNS · anti-steganalysis (StegExpose)ROC detectabilityImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy