Black-box genetic attacks flip 70% of correct fake detections in a retrained patch-based detector, GPT-4o reaches 73% AUC zero-shot on a Celeb-DF subset, and a 6.64% typographic attack degrades it.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Nearly Solved? Robust Deepfake Detection Requires More than Visual Forensics
Black-box genetic attacks flip 70% of correct fake detections in a retrained patch-based detector, GPT-4o reaches 73% AUC zero-shot on a Celeb-DF subset, and a 6.64% typographic attack degrades it.