Copy-move forgeries induce detectable spectral shifts in the normalized Laplacian of self-attention graphs from Stable Diffusion U-Nets, identifiable via Wasserstein distance to authentic reference spectra.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Spectral Forensics of Diffusion Attention Graphs for Copy-Move Forgery Detection
Copy-move forgeries induce detectable spectral shifts in the normalized Laplacian of self-attention graphs from Stable Diffusion U-Nets, identifiable via Wasserstein distance to authentic reference spectra.