提出双机制协同框架，提升伪造视频检测的公平性与准确性。
Decoupling Bias, Aligning Distributions: Synergistic Fairness Optimization for Deepfake Detection
- 通过解耦模型结构中的敏感通道，减少性别种族偏见影响。
- 在特征层面拉近全局样本与各群体分布距离，提升公平性。
- 兼顾检测精度与群体间公平性，适合数字身份安全场景应用。
公平性是深度伪造检测模型可信部署的核心要素，尤其在数字身份安全领域。当前检测模型对不同人口统计群体（如性别、种族）存在偏差，可能导致系统性误判，加剧数字鸿沟与社会不公。然而，现有增强公平性的方法常以牺牲检测准确率为代价。为此，本文提出一种双机制协同优化框架，创新性地结合结构公平解耦与全局分布对齐：在模型架构层面解耦对人口统计群体敏感的通道，并在特征层面减小整体样本分布与各群体分布之间的距离。实验表明，相较于其他方法，该框架在保持跨域整体检测准确率的同时，显著提升了组间与组内公平性。代码已开源：https://github.com/ywh1093/Fairness-Optimization。
原文摘要 · Abstract (English)
Fairness is a core element in the trustworthy deployment of deepfake detection models, especially in the field of digital identity security. Biases in detection models toward different demographic groups, such as gender and race, may lead to systemic misjudgments, exacerbating the digital divide and social inequities. However, current fairness-enhanced detectors often improve fairness at the cost of detection accuracy. To address this challenge, we propose a dual-mechanism collaborative optimization framework. Our proposed method innovatively integrates structural fairness decoupling and global distribution alignment: decoupling channels sensitive to demographic groups at the model architectural level, and subsequently reducing the distance between the overall sample distribution and the distributions corresponding to each demographic group at the feature level. Experimental results demonstrate that, compared with other methods, our framework improves both inter-group and intra-group fairness while maintaining overall detection accuracy across domains. The code is available at https://github.com/ywh1093/Fairness-Optimization.
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。