AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Editprint: General Digital Image Forensics via Editing Fingerprint with Self-Augmentation Training

Haiwei Wu, Kemou Li, Yuanman Li, Jiantao Zhou

CVPR 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Self-supervised neuroimaging representations

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
train on simulated in- and out-camera editing chains with language-guided contrastive learning, instead of labeled camera data (ExifMeta)self-supervised forensic features · SID open-set (mean over 10 generators)AUC: .8539 -> .9625Improved
replace ExifMeta with Editprint for social network provenanceExifMeta · SNP open-set, SDR (10 OSNs)AUC: .5092 -> .8120Improved
replace ExifMeta with Editprint for generation attributionExifMeta · SID generation attribution (10 generators)average F1: 0.8608 -> 0.9206Improved
Editprint trained without annotations versus supervised UniDetEditprint · SID open-set (mean over 10 generators)AUC: .9625 vs .9700No clear effect
Editprint (self-supervised) versus supervised SNP methodsEditprint · SNP open-set (mean AUC)AUC: .8853 vs .8952 (Seq2Seq), .8986 (MultiClue)No clear effect
Editprint versus ExifMeta for camera source identificationExifMeta · CSI open-set (mean of 4 test sets)AUC: .9211 -> .9199No clear effect
supervised SID methods versus Editprint on generation attributionEditprint · SID generation attribution (10 generators)F1: 0.9206 vs 0.9213 to 0.9529 (supervised)No clear effect
Editprint on diffusion-model detection (SD and MJ) is weaker than on GANsEditprint · SID open-setAUC: SD .8821, MJ .8454 vs StarGAN .9999Mixed

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