AI Paper Atlas

Research map / Image generation / GANs

What can Discriminator do? Towards Box-free Ownership Verification of Generative Adversarial Networks

Ziheng Huang, Boheng Li, Yan Cai, Run Wang, Shangwei Guo, Liming Fang, Jing Chen, Lina Wang

ICCV 2023 · Image generation › GANs · approach: Stabilized GAN training · 15 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
initialize hypersphere network and center from the paired discriminator instead of randomly (ablation)box-free GAN ownership verification · Ambiguity attack (different models)AUC (%): 57.21 -> 75.63Improved
use SOTA GAN architectures (StyleGAN family) rather than simple DCGANverification scheme · Different-model AUCAUC (%): AUC > 80%Improved
apply output image transformations (noise, blur, JPEG, crop) within acceptable qualityverification scheme · CelebA/LSUNAUC (%): 54.15 to 57.24 AUC across transformationsNo clear effect
prune GAN weights up to about 40%verification scheme · DCGAN CelebA 128AUC (%): AUC below 60% at about 40% pruningNo clear effect
train two GANs on different datasets (disjoint subsets)verification scheme · CelebA/LSUNAUC (%): AUC above 75%Improved
models differ only in initialization seedverification scheme · image synthesisAUC (%): about 60% vs less than 53% for identical modelsMixed

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