μFlow trains a normalizing flow on averaged real-image features to detect deepfakes via likelihood in a fully out-of-distribution setting.
ArXivabs/2503.19683(2025),https://api
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
S^3 extracts dominant shortcut directions from a linear forgery-method classifier using SVD and attenuates them in feature space to improve cross-method generalization in deepfake detection.
citing papers explorer
-
$\mu$Flow: Leveraging Average Images for Improving Generalisation of Deepfake Faces Detectors
μFlow trains a normalizing flow on averaged real-image features to detect deepfakes via likelihood in a fully out-of-distribution setting.
-
Suppressing Forgery-Specific Shortcuts for Generalizable Deepfake Detection
S^3 extracts dominant shortcut directions from a linear forgery-method classifier using SVD and attenuates them in feature space to improve cross-method generalization in deepfake detection.