构建大规模视频伪造检测基准，提升模型对未知伪造类型的泛化能力
Celeb-DF++: A Large-scale Challenging Video DeepFake Benchmark for Generalizable Forensics
- 涵盖三类主流伪造场景，使用22种不同生成方法制作高质量伪造视频
- 引入新评估协议，验证24种检测模型在跨类型伪造上的泛化性能短板
- 适合研究通用伪造检测、数据集设计与模型鲁棒性方向的学者参考
人工智能技术的快速发展显著增加了网络上深度伪造视频的多样性，对通用伪造检测（generalizable forensics）构成严峻挑战，即用单一模型检测大量未见过的伪造类型。现有数据集虽规模大，但伪造类型单一，难以支撑通用检测方法的发展。为此，我们在前期Celeb-DF基础上，推出新的大规模、高挑战性视频深度伪造基准Celeb-DF++，覆盖三种常见伪造场景：人脸替换（Face-swap, FS）、人脸重演（Face-reenactment, FR）和说话人合成（Talking-face, TF）。每类场景包含大量高质量伪造视频，共采用22种近期深度伪造方法生成，这些方法在架构、生成流程和目标面部区域上均有差异，涵盖现实世界中广泛存在的伪造案例。我们还设计了评估协议，用于衡量24种最新检测方法的泛化能力，揭示了现有方法的局限性及本数据集的挑战性。
原文摘要 · Abstract (English)
The rapid advancement of AI technologies has significantly increased the diversity of DeepFake videos circulating online, posing a pressing challenge for \textit{generalizable forensics}, \ie, detecting a wide range of unseen DeepFake types using a single model. Addressing this challenge requires datasets that are not only large-scale but also rich in forgery diversity. However, most existing datasets, despite their scale, include only a limited variety of forgery types, making them insufficient for developing generalizable detection methods. Therefore, we build upon our earlier Celeb-DF dataset and introduce {Celeb-DF++}, a new large-scale and challenging video DeepFake benchmark dedicated to the generalizable forensics challenge. Celeb-DF++ covers three commonly encountered forgery scenarios: Face-swap (FS), Face-reenactment (FR), and Talking-face (TF). Each scenario contains a substantial number of high-quality forged videos, generated using a total of 22 various recent DeepFake methods. These methods differ in terms of architectures, generation pipelines, and targeted facial regions, covering the most prevalent DeepFake cases witnessed in the wild. We also introduce evaluation protocols for measuring the generalizability of 24 recent detection methods, highlighting the limitations of existing detection methods and the difficulty of our new dataset.
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。