Towards Real-World Deepfake Detection: A Diverse In-the-wild Dataset of Forgery Faces

View on arXiv ← Back to list

Authors: Junyu Shi, Minghui Li, Junguo Zuo, Zhifei Yu, Yipeng Lin, Shengshan Hu, Ziqi Zhou, Yechao Zhang, Wei Wan, Yinzhe Xu, Leo Yu Zhang

Published: 2025-10-09 10:54:38+00:00

AI Summary

The paper introduces RedFace, a novel real-world-oriented facial deepfake dataset comprising over 60,000 forged images and 1,000 manipulated videos. It addresses the limitations of existing academic benchmarks by utilizing 9 commercial online platforms and bespoke algorithms to generate diverse, in-the-wild deepfakes. This dataset aims to bridge the gap between academic evaluations and the real-world necessity for robust deepfake detection.

Abstract

Deepfakes, leveraging advanced AIGC (Artificial Intelligence-Generated Content) techniques, create hyper-realistic synthetic images and videos of human faces, posing a significant threat to the authenticity of social media. While this real-world threat is increasingly prevalent, existing academic evaluations and benchmarks for detecting deepfake forgery often fall short to achieve effective application for their lack of specificity, limited deepfake diversity, restricted manipulation techniques.To address these limitations, we introduce RedFace (Real-world-oriented Deepfake Face), a specialized facial deepfake dataset, comprising over 60,000 forged images and 1,000 manipulated videos derived from authentic facial features, to bridge the gap between academic evaluations and real-world necessity. Unlike prior benchmarks, which typically rely on academic methods to generate deepfakes, RedFace utilizes 9 commercial online platforms to integrate the latest deepfake technologies found in the wild, effectively simulating real-world black-box scenarios.Moreover, RedFace's deepfakes are synthesized using bespoke algorithms, allowing it to capture diverse and evolving methods used by real-world deepfake creators. Extensive experimental results on RedFace (including cross-domain, intra-domain, and real-world social network dissemination simulations) verify the limited practicality of existing deepfake detection schemes against real-world applications. We further perform a detailed analysis of the RedFace dataset, elucidating the reason of its impact on detection performance compared to conventional datasets. Our dataset is available at: https://github.com/kikyou-220/RedFace.

Key findings

Extensive experiments on RedFace revealed that existing deepfake detection methods exhibit limited practicality and generalization capabilities against diverse, real-world deepfakes, showing significant performance degradation in cross-domain and degraded image quality scenarios. This underscores the urgent need for more robust and versatile deepfake detection technologies to cope with evolving real-world threats.

Approach

The authors created the RedFace dataset by first collecting diverse authentic facial features from CelebA. They then generated deepfakes by leveraging 9 commercial online platforms and bespoke algorithms, covering four main deepfake types: entire face synthesis, face swapping, face attribute manipulation, and face reenactment, to simulate real-world black-box scenarios and ensure diversity.

Datasets

RedFace, CelebA

Model(s)

UNKNOWN

Author countries

China, Australia

← Previous