AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

BiSLW: Bi-Spectral Latent Watermarking for Generative Diffusion Models

Aryan Pandit

ECCV 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
Embed watermark in both low- and high-frequency latent bands vs low only (ablation)BiSLW · AI-generated images 48-bitBit acc. (combined attack): 0.88 -> 0.93Improved
Embed in both bands vs high only (ablation)BiSLW · AI-generated images 48-bitBit acc. (combined attack): 0.90 -> 0.93Improved
Embed in both bands vs low only, on image quality (ablation)BiSLW · AI-generated images 48-bitPSNR: 38.96 -> 37.71Hurt
Increase latent fidelity weight lambda_z from 0.5 to 20 (ablation)BiSLW · AI-generated images 48-bitPSNR / combined accuracy: PSNR 36.85 -> 39.59; Comb acc 0.96 -> 0.88Mixed
Use spectral radius r=0.25 instead of 0.15 or 0.35 (ablation)BiSLW · AI-generated images 48-bitBit acc. (combined attack): 0.89 / 0.90 -> 0.93Improved
Increase embedding strength (alpha_L, alpha_H) from (0.6,0.2) to (1.0,0.5) (ablation)BiSLW · AI-generated imagesPSNR / combined accuracy: PSNR 38.20 -> 36.95; Comb acc 0.89 -> 0.95Mixed
Use average fusion instead of learned weighted fusion (ablation)BiSLW decoder · AI-generated images 48-bitBit acc. (combined attack): 0.93 -> 0.93No clear effect
Use average fusion instead of max fusion (ablation)BiSLW decoder · AI-generated images 48-bitBit acc. (combined attack): 0.92 -> 0.93Improved
Increase payload from 32 to 128 bits (ablation)BiSLW · AI-generated imagesPSNR / combined accuracy: PSNR 38.82 -> 36.34; Comb acc 0.98 -> 0.87Hurt
Replace LaWa with BiSLWLaWa* · AI-generated images 32-bitPSNR: 34.25 -> 37.40Improved
Replace LaWa with BiSLW against diffusion regeneration t*=250LaWa* · Regeneration attackBit accuracy: 0.94 -> 0.96Improved

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