无需性别年龄标签，用面部特征自动校准深伪检测偏差
Toward Calibrated, Fair, and accurate Deepfake Detection
- 基于冻结的面部嵌入做日志重映射，无须标注性别年龄
- 在跨数据集测试中，最低群体准确率提升12.3%，误报率差距缩小58%
- 适合作为任何检测器的即插即用模块，部署成本极低
深伪检测模型在不同人口群体间表现差异显著。现有公平性方法依赖人口属性标签、重新训练或牺牲整体精度。本文提出Face-Fairness（FF）框架，一种无需标签的即插即用偏差缓解方案。核心方法Face-Feature Tuning（FFT）首次实现无标签公平性：通过冻结的面部嵌入对输出日志进行轻量级重映射。此外还设计两种变体：当有标签时使用FF-Max最大化最差组准确率；当无标签时使用FF-Discover基于嵌入发现分组。在同域与跨数据集测试中，FF持续降低误报率/召回率差距，提升最低群体准确率，同时保持甚至提高整体准确率。该方法与检测器无关，运行开销可忽略，且无需访问身份属性。
原文摘要 · Abstract (English)
Deepfake detectors show large performance gaps across demographic groups. Existing fairness approaches require demographic labels, retraining, or sacrifice accuracy. We introduce Face-Fairness (FF), a plug-and-play framework for bias mitigation. Our primary contribution, Face-Feature Tuning (FFT), is the first demographic label-free fairness method demonstrated for deepfake detection: a lightweight calibrator that performs a logit remapping conditioned on frozen face embeddings. We complement FFT with two variants: FF-Max, which maximizes worst-group accuracy when demographics are available, and FF-Discover, which does the same with embedding-discovered groups. Across in-domain and cross-dataset test settings, FF consistently reduces FPR/TPR gaps and improves minimum group accuracy while maintaining (often improving) overall accuracy. The approach is detector-agnostic, adds negligible runtime overhead, and requires no access to identity attributes.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。