3260 papers • 126 benchmarks • 313 datasets
Attribute the origin (model/architecture) of fake images.
(Image credit: Papersgraph)
These leaderboards are used to track progress in fake-image-attribution
No benchmarks available.
Use these libraries to find fake-image-attribution models and implementations
No subtasks available.
Based on an observation that GAN architecture is likely to leave globally consistent fingerprints while traces left by model weights vary in different regions, a simple yet effective solution named by DNA-Det is provided to attribute fake images on architecture-level.
Adding a benchmark result helps the community track progress.