MFFI: Multi-Dimensional Face Forgery Image Dataset for Real-World Scenarios

MFFI: Multi-Dimensional Face Forgery Image Dataset for Real-World Scenarios

ACM International Conference on Multimedia

10.1145/3746027.3758280

https://dl.acm.org/doi/10.1145/3746027.3758280

changtao miao, weiwei feng, qi chu, Yi Zhang, man luo, kaiyuan zheng, tao gong, jianshu li, yunfeng diao, Wei Zhou, Joey Tianyi Zhou, xiaoshuai hao

deepfake, Face Forgery Detection, Real-World Scenarios

27 August 2025

Miao, C., Zhang, Y., Luo, M., Feng, W., Zheng, K., Chu, Q., Gong, T., Li, J., Diao, Y., Zhou, W., Zhou, J. T., & Hao, X. (2025). MFFI: Multi-Dimensional Face Forgery Image Dataset for Real-World Scenarios. MM ’25: Proceedings of the 33rd ACM International Conference on Multimedia, 13235–13242. https://doi.org/10.1145/3746027.3758280

Rapid advances in Artificial Intelligence Generated Content (AIGC) have enabled increasingly sophisticated face forgeries, posing a significant threat to social security. However, current Deepfake detection methods are limited by constraints in existing datasets, which lack the diversity necessary in real-world scenarios. Specifically, these datasets fall short in four key areas: unknown of advanced forgery techniques, variability of facial scenes, richness of real data, and degradation of real-world propagation. To address these challenges, we propose the Multi-dimensional Face Forgery Image (MFFI) dataset, tailored for real-world scenarios. MFFI enhances realism based on four strategic dimensions: 1) Wider Forgery Methods; 2) Varied Facial Scenes; 3) Diversified Authentic Data; 4) Multi-level Degradation Operations. MFFI integrates 50 different forgery methods and contains 1024K image samples. Benchmark evaluations show that MFFI outperforms existing public datasets in terms of scene complexity, cross-domain generalization capability, and detection difficulty gradients. These results validate the technical advance and practical utility of MFFI in simulating real-world conditions. Moreover, the proposed MFFI dataset served as the core benchmark for the Global Multimedia Deepfake Detection Challenge held on Kaggle. The dataset and additional details are publicly available at https://github.com/inclusionConf/MFFI.

Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)

This research / project is supported by the National Research Foundation - AI Singapore Programme
Grant Reference no. : AISG3-RP-2024-033

© 2025 Copyright held by the owner/author(s). This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in ACM International Conference on Multimedia, http://dx.doi.org/10.1145/3746027.3758280

https://oar.a-star.edu.sg/communities-collections/articles/22268

NA

Institute of High Performance Computing