A frozen CLIP model with prompts guided by GPT-4 concepts plus test-time prompt tuning achieves 0.911 average AUC and 0.774 overall accuracy on the DeepFakeFaceForensics benchmark.
Detection of gan-generated fake images over social networks,
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
-
Knowledge-Guided Prompt Learning for Deepfake Facial Image Detection
A frozen CLIP model with prompts guided by GPT-4 concepts plus test-time prompt tuning achieves 0.911 average AUC and 0.774 overall accuracy on the DeepFakeFaceForensics benchmark.