SPRINT achieves over 99% attribution accuracy on FFHQ images across multiple model pools while reducing adaptive attack success rates to 1% or below by keeping verification targets secret.
Fourier spectrum discrepancies in deep network generated images
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
SpInShield is a temporal spectral-invariant defense that decouples semantic motion from manipulatable spectral artifacts in deepfake detectors via a learnable adversary and shortcut suppression optimization.
citing papers explorer
-
SPRINT: Robust Model Attribution of Generated Images via Secret Pixel Reconstruction
SPRINT achieves over 99% attribution accuracy on FFHQ images across multiple model pools while reducing adaptive attack success rates to 1% or below by keeping verification targets secret.
-
Exposing and Mitigating Temporal Attack in Deepfake Video Detection
SpInShield is a temporal spectral-invariant defense that decouples semantic motion from manipulatable spectral artifacts in deepfake detectors via a learnable adversary and shortcut suppression optimization.