AI Paper Atlas

Research map / Image generation / GANs

Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints

Ning Yu, Larry S. Davis, Mario Fritz

ICCV 2019 · Image generation › GANs · approach: GAN-based image manipulation · 530 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
restrict to low-frequency band at downsample factor 8 (16x16) instead of full image (ablation)attribution network · CelebA seed setupaccuracy (%): 99.14 -> 87.20Hurt
use high-frequency residual instead of low-frequency band at 16x16 (ablation)attribution network · CelebA seed setupaccuracy (%): 87.20 -> 92.90Improved
use high-frequency residual instead of low-frequency band at 32x32 (ablation)attribution network · LSUN seed setupaccuracy (%): 91.08 -> 96.04Improved
restrict to 4x4 low-frequency band (ablation)attribution network · CelebA seed setupaccuracy (%): 99.14 -> 26.58Hurt
reduce patch size from 128x128 to 24x24 (ablation)post-pooling network · CelebA seed setupaccuracy (%): 99.34 -> 99.24No clear effect
reduce patch size from 128x128 to 24x24 (ablation)post-pooling network · LSUN seed setupaccuracy (%): 97.44 -> 88.36Hurt
reduce patch size to 3x3 (ablation)post-pooling network · CelebA seed setupaccuracy (%): 99.34 -> 13.42Hurt
evaluate on the 10% artifact-free selected images instead of all images (ablation)attribution network · CelebA seed setupaccuracy (%): 99.14 -> 99.93No clear effect
evaluate on the 10% artifact-free selected images instead of all images (ablation)attribution network · LSUN seed setupaccuracy (%): 97.04 -> 98.16No clear effect
fine-tune classifier against noise attack (immunize) (ablation)attribution network · CelebA noise attackaccuracy (%): 9.14 -> 93.02Improved
fine-tune classifier against JPEG compression attack (immunize) (ablation)attribution network · CelebA compression attackaccuracy (%): 8.77 -> 88.02Improved
fine-tune classifier against combination attack (immunize) (ablation)attribution network · CelebA combination attackaccuracy (%): 19.31 -> 72.64Improved

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