Scalable Face Security Vision Foundation Model for Deepfake, Diffusion, and Spoofing Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Gaojian, Lin, Feng, Wu, Tong, Yan, Zhisheng, Ren, Kui
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908588992102400
author Wang, Gaojian
Lin, Feng
Wu, Tong
Yan, Zhisheng
Ren, Kui
author_facet Wang, Gaojian
Lin, Feng
Wu, Tong
Yan, Zhisheng
Ren, Kui
contents With abundant, unlabeled real faces, how can we learn robust and transferable facial representations to boost generalization across various face security tasks? We make the first attempt and propose FS-VFM, a scalable self-supervised pre-training framework, to learn fundamental representations of real face images. We introduce three learning objectives, namely 3C, that synergize masked image modeling (MIM) and instance discrimination (ID), empowering FS-VFM to encode both local patterns and global semantics of real faces. Specifically, we formulate various facial masking strategies for MIM and devise a simple yet effective CRFR-P masking, which explicitly prompts the model to pursue meaningful intra-region Consistency and challenging inter-region Coherency. We present a reliable self-distillation mechanism that seamlessly couples MIM with ID to establish underlying local-to-global Correspondence. After pre-training, vanilla vision transformers (ViTs) serve as universal Vision Foundation Models for downstream Face Security tasks: cross-dataset deepfake detection, cross-domain face anti-spoofing, and unseen diffusion facial forensics. To efficiently transfer the pre-trained FS-VFM, we further propose FS-Adapter, a lightweight plug-and-play bottleneck atop the frozen backbone with a novel real-anchor contrastive objective. Extensive experiments on 11 public benchmarks demonstrate that our FS-VFM consistently generalizes better than diverse VFMs, spanning natural and facial domains, fully, weakly, and self-supervised paradigms, small, base, and large ViT scales, and even outperforms SOTA task-specific methods, while FS-Adapter offers an excellent efficiency-performance trade-off. The code and models are available on https://fsfm-3c.github.io/fsvfm.html.
format Preprint
id arxiv_https___arxiv_org_abs_2510_10663
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Scalable Face Security Vision Foundation Model for Deepfake, Diffusion, and Spoofing Detection
Wang, Gaojian
Lin, Feng
Wu, Tong
Yan, Zhisheng
Ren, Kui
Computer Vision and Pattern Recognition
Artificial Intelligence
I.4.10; I.2.10; I.5.0
With abundant, unlabeled real faces, how can we learn robust and transferable facial representations to boost generalization across various face security tasks? We make the first attempt and propose FS-VFM, a scalable self-supervised pre-training framework, to learn fundamental representations of real face images. We introduce three learning objectives, namely 3C, that synergize masked image modeling (MIM) and instance discrimination (ID), empowering FS-VFM to encode both local patterns and global semantics of real faces. Specifically, we formulate various facial masking strategies for MIM and devise a simple yet effective CRFR-P masking, which explicitly prompts the model to pursue meaningful intra-region Consistency and challenging inter-region Coherency. We present a reliable self-distillation mechanism that seamlessly couples MIM with ID to establish underlying local-to-global Correspondence. After pre-training, vanilla vision transformers (ViTs) serve as universal Vision Foundation Models for downstream Face Security tasks: cross-dataset deepfake detection, cross-domain face anti-spoofing, and unseen diffusion facial forensics. To efficiently transfer the pre-trained FS-VFM, we further propose FS-Adapter, a lightweight plug-and-play bottleneck atop the frozen backbone with a novel real-anchor contrastive objective. Extensive experiments on 11 public benchmarks demonstrate that our FS-VFM consistently generalizes better than diverse VFMs, spanning natural and facial domains, fully, weakly, and self-supervised paradigms, small, base, and large ViT scales, and even outperforms SOTA task-specific methods, while FS-Adapter offers an excellent efficiency-performance trade-off. The code and models are available on https://fsfm-3c.github.io/fsvfm.html.
title Scalable Face Security Vision Foundation Model for Deepfake, Diffusion, and Spoofing Detection
topic Computer Vision and Pattern Recognition
Artificial Intelligence
I.4.10; I.2.10; I.5.0
url https://arxiv.org/abs/2510.10663