Attributing Fake Images to GANs¶
Yu, N., Davis, L., & Fritz, M. (2019). Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints. IEEE/CVF International Conference on Computer Vision, 7556-7566.
Cited by¶
1 citation across 1 artifact.
Each citation links to the sentence it supports in the citing article.
Mechanisms¶
- Model-Output Signature Probe
- Analysts sample thousands of fresh outputs across many random seeds and prompts, then look for a recurrent artifact — say, a characteristic pattern in the frequency spectrum left by the model's upsampling layers, the kind of residue researchers have called a "GAN fingerprint."
This sourceYu, Davis, and Fritz show that GAN instances leave stable, model-specific fingerprints in generated images that can support source attribution.
- Analysts sample thousands of fresh outputs across many random seeds and prompts, then look for a recurrent artifact — say, a characteristic pattern in the frequency spectrum left by the model's upsampling layers, the kind of residue researchers have called a "GAN fingerprint."
Verification¶
Does it exist? Confirmed. This work's DOI resolves to a registered record, which fixes its identity. That is all it fixes.
Does it back the claim? Not recorded. The single citation of this work carries no recorded support check.
Support is checked per citation rather than per work — the same source can be cited soundly in one article and wrongly in another. Per-citation recording began recently, so a citation with no recorded check is a gap in the record rather than evidence it went unchecked.
See how references were verified.
Registry ID ref:46b71e03a48b · see in the full table