Face enhancement filters and GAN beautification can act as anti-forensic attacks, raising deepfake detector misclassification of fake frames to as high as 87% in some settings.
Deep learning-based counter anti- forensic of gan-based attack in hevc compressed domain using coding pattern analysis
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Realism to Deception: Investigating Deepfake Detectors Against Face Enhancement
Face enhancement filters and GAN beautification can act as anti-forensic attacks, raising deepfake detector misclassification of fake frames to as high as 87% in some settings.