Score: 2

Celeb-DF++: A Large-scale Challenging Video DeepFake Benchmark for Generalizable Forensics

Published: July 24, 2025 | arXiv ID: 2507.18015v1

By: Yuezun Li , Delong Zhu , Xinjie Cui and more

Potential Business Impact:

Spots fake videos made by many different AI tools.

Business Areas:
Facial Recognition Data and Analytics, Software

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.

Country of Origin
πŸ‡ΊπŸ‡Έ πŸ‡¨πŸ‡³ China, United States

Repos / Data Links

Page Count
12 pages

Category
Computer Science:
CV and Pattern Recognition