A learned preprocessing module restores image forgery localization accuracy under several white-box adversarial attacks while barely changing results on clean forged images.
DOA-GAN: Dual-order attentive generative adversarial network for image copy-move forgery detection and localization,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Active Adversarial Noise Suppression for Image Forgery Localization
A learned preprocessing module restores image forgery localization accuracy under several white-box adversarial attacks while barely changing results on clean forged images.