AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Training-Free Coverless Multi-Image Steganography with Access Control

Minyeol Bae, Si-Hyeon Lee

ICML 2026 · Image generation › Autoregressive and latent generation · approach: Robust diffusion watermarking · 0 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 Random Basis plus Latent Vector Fusion instead of concatenation with Noise Flip (MIDAS vs DiffStega*)training-free coverless steganography · Stego260 (N=2) stego diversityPSNR between stego and secret (lower is more diverse): 17.065 -> 9.885Improved
use MIDAS instead of DiffStega* for access controlmulti-image hiding · Stego260 (N=2) wrong-key reconstructionPSNR (lower is better): 18.137 -> 9.964Improved
increase number of secret images N from 1 to 4 for DiffStega*DiffStega* · Stego260MANIQA: 0.450 -> 0.364Hurt
increase number of secret images N from 1 to 4 for MIDASMIDAS · Stego260MANIQA: 0.429 -> 0.479Improved
MIDAS vs modification-based IIS under Gaussian noiseaccess-controlled steganography · Stego260 (N=2) robustnessPSNR (dB): 12.439 -> 20.046Improved
MIDAS vs DiffStega* under Gaussian noiserobustness · Stego260 (N=2)PSNR (dB): 20.076 -> 20.046No clear effect
MIDAS vs modification-based IIS/AIS for reconstruction on clean imagesreconstruction quality · Stego260 (N=2)PSNR (correct key): 41.360 (IIS) -> 23.903Hurt
MIDAS vs CRoSS*/DiffStega* in steganalysis resistancestego images · XuNet and SiaStegNet accuracysteganalysis accuracy: about 20% lower than baselinesImproved
use Random Basis strength gamma 0.4 in security analysis (ablation)Random Basis · Stego260information leakageImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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