AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

KIStego: Key-Independent Secure Image Distribution via Bipartite Structural Invariants

Ren Lijing, Denghui Zhang

ICML 2026 · Image generation › Fast diffusion sampling · approach: Distributional control of diffusion

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 bipartite shares with orthogonal Gaussian mapping instead of key-dependent ODE inversionKIStego · UniStega recoveryPSNR: 23.9374 (DiffStega) -> 24.2491Improved
decouple secret from stego-image via sharesKIStego · UniStega concealmentID similarity: 0.2255 (DiffStega) -> 0.0106Improved
use KIStego against steganalysis detectorsKIStego · UniStega steganalysisdetection accuracy: 0.582 (CRoSS) -> 0.502 on SRNetImproved
anchor payload to discrete structural invariants under channel degradationKIStego · UniStega JPEG Q=70PSNR: 21.16 (DiffStega) -> 23.14Improved
add differentiable sigmoid measurement surrogate instead of unguided latent DPS (ablation)KIStego · Guidance ablationPSNR: 18.56 -> 24.25Improved
replace straight-through error-diffusion gradient with differentiable surrogate (ablation)KIStego · Guidance ablationPSNR: 21.12 -> 24.25Improved
increase payload density to 4.0 BPP via spatial multiplexing of 8 shares (ablation)KIStego · UniStega capacityPSNR: 24.25 -> 20.15Hurt
apply measurement guidance every 10 steps (efficient mode) (ablation)KIStego · Recovery latencylatency: approximately 30% lower latencyImproved
use modification-based embedding (HiNet) under channel degradationHiNet · UniStega robustnessPSNR: 46.15 -> 10.26 under blurHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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