Scholarlink

This study investigates the correlation between misclassifications in DeepFake detection and high-level facial attributes. A pre-trained frame-level classifier is used to distinguish between manipulated and authentic video contents and its wrong predictions are analyzed in detail. To enrich the dataset, we automatically annotate each video with additional labels, including gender, hair color, hair length, ear visibility and ethnicity, using a semi-supervised facial attribute recognition pipeline. An analysis of how misclassified video segments cross-reference with the visual attribute labels to identify emerging patterns is provided. Valuable insights for future bias-aware training strategies and more interpretable DeepFake detection systems are finally given.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Analysis of DeepFake Detection Through Semi-supervised Facial Attribute Labeling

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Vittorio Stile,
  • Roberto Caldelli,
  • Gabriel Guerrero-Contreras,
  • Sara Balderas-Díaz,
  • Inmaculada Medina-Bulo

摘要

This study investigates the correlation between misclassifications in DeepFake detection and high-level facial attributes. A pre-trained frame-level classifier is used to distinguish between manipulated and authentic video contents and its wrong predictions are analyzed in detail. To enrich the dataset, we automatically annotate each video with additional labels, including gender, hair color, hair length, ear visibility and ethnicity, using a semi-supervised facial attribute recognition pipeline. An analysis of how misclassified video segments cross-reference with the visual attribute labels to identify emerging patterns is provided. Valuable insights for future bias-aware training strategies and more interpretable DeepFake detection systems are finally given.