Optimizing the initial latent noise of a diffusion model creates on-manifold adversarial examples that, added to training, make AIGC detectors generalize much better to unseen generators.
DRCT: Diffusion reconstruction contrastive training towards universal detection of diffusion generated images
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
-
Breaking Latent Prior Bias in Detectors for Generalizable AIGC Image Detection
Optimizing the initial latent noise of a diffusion model creates on-manifold adversarial examples that, added to training, make AIGC detectors generalize much better to unseen generators.