AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Attack-Resistant Watermarking for AIGC Image Forensics via Diffusion-based Semantic Deflection

Qingyu Liu, Yitao Zhang, Zhongjie Ba, Chao Shuai, Peng Cheng, Tianhang Zheng, Zhibo Wang

ICLR 2026 · Image generation › Autoregressive and latent generation · approach: Robust diffusion watermarking · 1 citations (OpenAlex)

Read the paper

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 PAI's multi-dimensional latent-space verification instead of scalar-threshold verification (Gaussian Shading)PAI vs Gaussian Shading · Spoofing attacks (average)ownership ACC (%): 15.77 -> 96.33Improved
Use PAI instead of Stable Signature under removal attacksPAI vs Stable Signature · Removal attacks (average)ownership ACC (%): 43.95 -> 99.00Improved
Use PAI instead of EditGuard on full-image semantic editing (Stable Inpainting)PAI vs EditGuard · Tamper localization (Stable Inpainting)F1 (%): 34.00 -> 80.00Improved
Use PAI instead of EditGuard on partial edits (PS)PAI vs EditGuard · Tamper localization (PS)F1 (%): 86.07 -> 66.24Hurt
Use PAI instead of EditGuard on average tamper localizationPAI vs EditGuard · Tamper localization (average)AUC (%): 75.77 -> 89.77Improved
Use PAI instead of Gaussian Shading on image quality (FID) on CelebA-HQPAI vs Gaussian Shading · CelebA-HQ (clean)FID: 23.72 -> 21.37Improved
Randomly tamper the saved timestamp on watermarked images (ablation)PAI · Adaptive attack (timestamp tampering)ownership verification accuracy: remained 100%No clear effect
Embedded baselines under unseen degradation such as blur versus inherent schemesEditGuard · Image degradation (blur)ownership verification accuracyHurt

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