简单方法调优后在真实场景检测深伪视频，准确率超80%。
Revisiting Simple Baselines for In-The-Wild Deepfake Detection
- 用预训练视觉模型微调，不依赖复杂架构
- 在Deepfake-Eval-2024上达81%准确率
- 适合追求实用与可解释性的部署场景
合成媒体的广泛使用需要可访问的深度伪造检测工具和真实场景基准。尽管多数研究在高度控制的数据集上评估检测器，本文聚焦近期发布的“真实场景”基准Deepfake-Eval-2024。初始报告显示，三个微调的开源模型准确率在61%至69%之间，显著低于领先商业检测器的82%。本文重新审视其中一种基线方法——Ojha等提出的通用预训练视觉骨干网络适配方案。通过更优的超参数调优，该方法在Deepfake-Eval-2024上实现81%准确率，相比原报告提升18个百分点，达到与商业检测器相当水平。文章讨论了准确率、计算成本与可解释性之间的权衡，探讨其在真实环境部署的实用性。代码已公开于https://github.com/Deepfake-Detection-KKO/deepfake-detection。
原文摘要 · Abstract (English)
The widespread adoption of synthetic media demands accessible deepfake detectors and realistic benchmarks. While most existing research evaluates deepfake detectors on highly controlled datasets, we focus on the recently released "in-the-wild" benchmark, Deepfake-Eval-2024. Initial reporting on Deepfake-Eval-2024 showed that three finetuned open-source models achieve accuracies between 61% and 69%, significantly lagging behind the leading commercial deepfake detector with 82% accuracy. Our work revisits one of these baseline approaches, originally introduced by Ojha et al., which adapts standard pretrained vision backbones to produce generalizable deepfake detectors. We demonstrate that with better-tuned hyperparameters, this simple approach actually yields much higher performance -- 81% accuracy on Deepfake-Eval-2024 -- surpassing the previously reported accuracy of this baseline approach by 18% and competing with commercial deepfake detectors. We discuss tradeoffs in accuracy, computational costs, and interpretability, focusing on how practical these deepfake detectors might be when deployed in real-world settings. Our code can be found at https://github.com/Deepfake-Detection-KKO/deepfake-detection.
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。