AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Forensic-Friendly Image Manipulation via Controllable Latent Diffusion

Hanyu Chen, Haiwei Wu, Jinyu Tian, Jianqing LI, Jiantao Zhou

CVPR 2026 · Image generation › Autoregressive and latent generation · approach: Robust diffusion watermarking

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 FFIM instead of the DDPM baseline for the in-domain forensic modelDDPM editing · AniCOCO, TruForF1: .570 -> .700Improved
post-hoc ReLoc enhancement of edited imagesDDPM editing · AniCOCO, TruForF1: .570 -> .557Hurt
ReLoc across localization forensicsDDPM editing · Pixel-level localization (four datasets)F1Mixed
FFIM on image-level detectorsDDPM editing · Image-level detection (CNND, UFD, DRCT)AUC: +14.8%, +13.5%, +27.3% AUCImproved
ReLoc on image-level detectorsDDPM editing · Image-level detection (CNND, UFD, DRCT)AUC: +5.9%, +11.8%, -6.2% AUCMixed
add FFIM to the editing processDDPM editing · User study (20 participants)satisfaction score: 4.15 vs 4.17, 4.10, 4.21No clear effect
add controllable projection to explicit guidance (ablation)FFIM with TruFor guidance · AniCOCO, TruForF1: .619 -> .700Improved
add explicit guidance on top of controllable projection (ablation)FFIM · AniCOCO, TruForF1: .570 -> .700Improved
use l-infinity norm projection instead of l2 (ablation)FFIM · AniCOCO, TruForF1: .700 -> .900Mixed
use cosine-similarity projection instead of l2 (ablation)FFIM · AniCOCO, TruForF1: .700 -> .599Hurt
use l1 instead of l2 norm projection (ablation)FFIM · AniCOCO, TruForF1: .700 -> .700No clear effect
apply FFIM with DPM denoising (ablation)DPM · AniCOCO, TruForF1: .568 -> .692Improved

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