MIFAE-Forensics: Masked Image-Frequency AutoEncoder for DeepFake Detection

自编码 计算机科学 图像(数学) 人工智能 模式识别(心理学) 计算机视觉 人工神经网络
作者
Hanyi Wang,Zihan Liu,Shilin Wang
出处
期刊: [Institute of Electrical and Electronics Engineers]
卷期号:: 1-5 被引量:7
标识
DOI:10.1109/icassp49660.2025.10889125
摘要

With continuously evolving generative models and increasingly diverse face forgery products, there is a growing demand for DeepFake detectors with stronger generalization ability and robustness. Previous works mainly capture method-specific forgery artifacts in the training set, thus failing to generalize well to unseen manipulations. In this paper, our key insight is that exploring common characteristics of natural faces is more ideal to alleviate overfitting rather than relying on specific forgery clues, as all sorts of manipulated images have intrinsic distributional differences from those captured by cameras. Hence, we propose a two-stage method, termed MIFAE-Forensics. Specifically, it reconstructs both facial semantics and local details from masked facial regions and high-frequency components, respectively, aiming to capture natural facial consistency in spatial domain and high-frequency details in frequency domain simultaneously. This facilitates the learning of a robust and transferable facial representation specialized for DeepFake detection. Subsequently, the pre-trained model is further fine-tuned to perform binary forgery classification along with reconstructing real faces in spatial domain, which ensures that the detector can maintain the ability to model real faces and encourages it to make decisions based on reconstruction discrepancies. Extensive experiments show superior results over state-of-the-arts on a wide range of DeepFake detection benchmarks. Our code is available at https://github.com/Mark-Dou/Forensics.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
cdercder的应助被nissy采纳,获得10
刚刚
1秒前
2秒前
干就完完成签到,获得积分20
2秒前
2秒前
明天太好完成签到,获得积分10
2秒前
yi发布了新的文献求助10
2秒前
隐形曼青的应助被Present采纳,获得30
3秒前
hyper完成签到 ,获得积分10
3秒前
3秒前
123发布了新的文献求助10
3秒前
3秒前
大模型的应助被LLL采纳,获得10
3秒前
3秒前
4秒前
4秒前
碎觉觉发布了新的文献求助30
4秒前
4秒前
顺利毕业发布了新的文献求助10
4秒前
5秒前
Moonber发布了新的文献求助10
5秒前
Linus完成签到,获得积分10
6秒前
千空发布了新的文献求助10
7秒前
7秒前
7秒前
干就完发布了新的文献求助10
7秒前
钟梓袄发布了新的文献求助10
7秒前
任我完成签到,获得积分10
7秒前
7秒前
Chelseacyh发布了新的文献求助10
8秒前
8秒前
孟滴滴的应助被颜凡桃采纳,获得10
8秒前
8秒前
领导范儿的应助被灰灰采纳,获得10
8秒前
ccl完成签到,获得积分10
8秒前
Owen的应助被KX采纳,获得10
9秒前
吴赫轩完成签到,获得积分20
9秒前
烟花的应助被Miraitowa采纳,获得10
9秒前
10秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Improving the wear resistance of vehicle gear oil by oil soluble LaF3 nanoparticles and typical additives of gear oil 500
Boundaries and Bodhisattvas 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8183204
求助须知:如何正确求助?哪些是违规求助? 9572434
关于积分的说明 21825655
捐赠科研通 7779988
什么是DOI,文献DOI怎么找? 3433852
关于科研通互助平台的介绍 2558060
邀请新用户注册赠送积分活动 2480148