DeepShield: Fortifying Deepfake Video Detection with Local and Global Forgery Analysis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cai, Yinqi, Li, Jichang, Li, Zhaolun, Chen, Weikai, Lan, Rushi, Xie, Xi, Luo, Xiaonan, Li, Guanbin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917218859614208
author Cai, Yinqi
Li, Jichang
Li, Zhaolun
Chen, Weikai
Lan, Rushi
Xie, Xi
Luo, Xiaonan
Li, Guanbin
author_facet Cai, Yinqi
Li, Jichang
Li, Zhaolun
Chen, Weikai
Lan, Rushi
Xie, Xi
Luo, Xiaonan
Li, Guanbin
contents Recent advances in deep generative models have made it easier to manipulate face videos, raising significant concerns about their potential misuse for fraud and misinformation. Existing detectors often perform well in in-domain scenarios but fail to generalize across diverse manipulation techniques due to their reliance on forgery-specific artifacts. In this work, we introduce DeepShield, a novel deepfake detection framework that balances local sensitivity and global generalization to improve robustness across unseen forgeries. DeepShield enhances the CLIP-ViT encoder through two key components: Local Patch Guidance (LPG) and Global Forgery Diversification (GFD). LPG applies spatiotemporal artifact modeling and patch-wise supervision to capture fine-grained inconsistencies often overlooked by global models. GFD introduces domain feature augmentation, leveraging domain-bridging and boundary-expanding feature generation to synthesize diverse forgeries, mitigating overfitting and enhancing cross-domain adaptability. Through the integration of novel local and global analysis for deepfake detection, DeepShield outperforms state-of-the-art methods in cross-dataset and cross-manipulation evaluations, achieving superior robustness against unseen deepfake attacks. Code is available at https://github.com/lijichang/DeepShield.
format Preprint
id arxiv_https___arxiv_org_abs_2510_25237
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DeepShield: Fortifying Deepfake Video Detection with Local and Global Forgery Analysis
Cai, Yinqi
Li, Jichang
Li, Zhaolun
Chen, Weikai
Lan, Rushi
Xie, Xi
Luo, Xiaonan
Li, Guanbin
Computer Vision and Pattern Recognition
Recent advances in deep generative models have made it easier to manipulate face videos, raising significant concerns about their potential misuse for fraud and misinformation. Existing detectors often perform well in in-domain scenarios but fail to generalize across diverse manipulation techniques due to their reliance on forgery-specific artifacts. In this work, we introduce DeepShield, a novel deepfake detection framework that balances local sensitivity and global generalization to improve robustness across unseen forgeries. DeepShield enhances the CLIP-ViT encoder through two key components: Local Patch Guidance (LPG) and Global Forgery Diversification (GFD). LPG applies spatiotemporal artifact modeling and patch-wise supervision to capture fine-grained inconsistencies often overlooked by global models. GFD introduces domain feature augmentation, leveraging domain-bridging and boundary-expanding feature generation to synthesize diverse forgeries, mitigating overfitting and enhancing cross-domain adaptability. Through the integration of novel local and global analysis for deepfake detection, DeepShield outperforms state-of-the-art methods in cross-dataset and cross-manipulation evaluations, achieving superior robustness against unseen deepfake attacks. Code is available at https://github.com/lijichang/DeepShield.
title DeepShield: Fortifying Deepfake Video Detection with Local and Global Forgery Analysis
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.25237