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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Miao, Changtao, Zhang, Yi, Luo, Man, Feng, Weiwei, Zheng, Kaiyuan, Chu, Qi, Gong, Tao, Li, Jianshu, Diao, Yunfeng, Zhou, Wei, Zhou, Joey Tianyi, Hao, Xiaoshuai
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911141056217088
author Miao, Changtao
Zhang, Yi
Luo, Man
Feng, Weiwei
Zheng, Kaiyuan
Chu, Qi
Gong, Tao
Li, Jianshu
Diao, Yunfeng
Zhou, Wei
Zhou, Joey Tianyi
Hao, Xiaoshuai
author_facet Miao, Changtao
Zhang, Yi
Luo, Man
Feng, Weiwei
Zheng, Kaiyuan
Chu, Qi
Gong, Tao
Li, Jianshu
Diao, Yunfeng
Zhou, Wei
Zhou, Joey Tianyi
Hao, Xiaoshuai
contents 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 data sets 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 (\textbf{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. The dataset and additional details are publicly available at {https://github.com/inclusionConf/MFFI}.
format Preprint
id arxiv_https___arxiv_org_abs_2509_05592
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MFFI: Multi-Dimensional Face Forgery Image Dataset for Real-World Scenarios
Miao, Changtao
Zhang, Yi
Luo, Man
Feng, Weiwei
Zheng, Kaiyuan
Chu, Qi
Gong, Tao
Li, Jianshu
Diao, Yunfeng
Zhou, Wei
Zhou, Joey Tianyi
Hao, Xiaoshuai
Computer Vision and Pattern Recognition
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 data sets 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 (\textbf{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. The dataset and additional details are publicly available at {https://github.com/inclusionConf/MFFI}.
title MFFI: Multi-Dimensional Face Forgery Image Dataset for Real-World Scenarios
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.05592