AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Open-Unfairness Adversarial Mitigation for Generalized Deepfake Detection

Zhaoyang Li, Zhu Teng, Baopeng Zhang, Jianping Fan

ICCV 2025 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Local Adversarial Learning (ablation)AdvOU · CDF/DFDC/DFD frame-level avgAUC: 75.65 -> 80.04Improved
add Global Relation Debiasing loss (Lro) (ablation)AdvOU · CDF/DFDC/DFD frame-level avgAUC: 77.66 -> 80.04Improved
add Unfairness Relation Amplification (ablation)AdvOU · CDF/DFDC/DFD frame-level avgAUC: 77.67 -> 80.04Improved
use lightweight Unfairness Regulator on frozen detector instead of fully trainable discoverer (ablation)AdvOU · CDF/DFDC/DFD frame-level avgAUC: 76.01 -> 80.04Improved
train unfairness discoverer on both real and fake samples instead of one source (ablation)AdvOU · CDF/DFDC/DFD frame-level avgAUC: 78.00 / 77.64 -> 80.04Improved
plug AdvOU into F3NetF3Net · CDF, DFDCP, DFDC, DFD avgAUC: 72.10 -> 77.29Improved
plug AdvOU into UIA-VITUIA-VIT · CDF, DFDCP, DFDC, DFD avgAUC: 77.14 -> 80.23Improved
plug AdvOU into EfficientNet-B4EfficientNet-B4 · DFDAUC: 84.95 -> 84.60No clear effect
AdvOU open-unfairness mitigation on EfficientNet-B3EfficientNet-B3 · CDF open-unfairnessFFPR: 88.45 -> 13.6Improved
AdvOU vs UDD with single ViTAdvOU ViT · DFDC video-levelAUC: 81.2 (UDD) vs 79.1 (Ours); CDF 93.1 vs 93.9Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy