AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Where Did I Come From? Origin Attribution of AI-Generated Images

Zhenting Wang, Chen Chen, Yi Zeng, Lingjuan Lyu, Shiqing Ma

NeurIPS 2023 · Image generation › Autoregressive and latent generation · approach: Generalizable fake image detection · 4 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
Use MSE instead of SSIM as reconstruction distance (ablation)RONAN · StyleGAN2-ADA CIFAR-10detection accuracy: 85.5% -> 97.0%Improved
Use MSE instead of MAE (ablation)RONAN · StyleGAN2-ADA CIFAR-10detection accuracy: 94.5% -> 97.0%Improved
Use MSE instead of LPIPS (ablation)RONAN · StyleGAN2-ADA CIFAR-10detection accuracy: 96.0% -> 97.0%Improved
Add reconstruction loss calibration (ablation)RONAN · Stable Diffusion v2detection accuracy: 75.0% -> 87.5%Improved
Replace DDIM inversion with RONAN reverse-engineering (ablation)Stable Diffusion v2 inversion · Stable Diffusion v2detection accuracy: 55.5% -> 87.5%Improved
Replace Parmar et al. inversion with RONAN reverse-engineering (ablation)Stable Diffusion v2 inversion · Stable Diffusion v2detection accuracy: 62.5% -> 87.5%Improved
Optimize in W+ space instead of Z space (ablation)RONAN on StyleGAN2-ADA · CIFAR-10detection accuracy: 97.0% -> 96.0%No clear effect
Optimize in W+ space instead of Z space (ablation)RONAN on StyleGAN XL · ImageNetdetection accuracy: 93.0% -> 93.5%No clear effect
Change reference model for calibration (Consistency Model, StyleGAN XL, Stable Diffusion) (ablation)RONAN · StyleGAN2-ADA CIFAR-10detection accuracy: 97.0%, 95.0%, 96.0%No clear effect
Use 2D entropy instead of reference model as complexity measure (ablation)RONAN · StyleGAN2-ADA CIFAR-10detection accuracy: 97.0%No clear effect
Increase training data overlap of M2 with M1 from 50% to 90%RONAN · DCGAN CIFAR-10detection accuracy: 98.5% -> 96.5%No clear effect
Increase box blur size from 1 to 4RONAN under adaptive attack · DCGAN CIFAR-10detection accuracy: 92.5% -> 53.5%Hurt

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