Face-Feature Tuning is a label-free logit remapping method that reduces FPR/TPR gaps across groups in deepfake detection while preserving overall accuracy.
arXiv:1901.08971 [cs]
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Introduces the CIFAR Synthetic Evidence Corpus, a multi-family dataset of AI-manipulated documents with source-separated train/test splits for evaluating detectors of AI-generated legal evidence.
ANL uses diffusion noise prediction and attention to regularize deepfake detectors for better generalization to unseen synthesis methods without added inference cost.
citing papers explorer
-
Toward Calibrated, Fair, and accurate Deepfake Detection
Face-Feature Tuning is a label-free logit remapping method that reduces FPR/TPR gaps across groups in deepfake detection while preserving overall accuracy.
-
The CIFAR Synthetic Evidence Corpus for Detecting AI-Generated Evidence
Introduces the CIFAR Synthetic Evidence Corpus, a multi-family dataset of AI-manipulated documents with source-separated train/test splits for evaluating detectors of AI-generated legal evidence.
-
Deepfake Detection Generalization with Diffusion Noise
ANL uses diffusion noise prediction and attention to regularize deepfake detectors for better generalization to unseen synthesis methods without added inference cost.