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

TL;DR

DeepShield is a deepfake detection framework that combines local artifact analysis and global forgery diversification to improve robustness and generalization across unseen deepfake videos.

Contribution

It introduces a novel dual-component approach, LPG and GFD, enhancing the CLIP-ViT encoder for better cross-domain deepfake detection.

Findings

Outperforms state-of-the-art methods in cross-dataset evaluations

Achieves higher robustness against unseen deepfake manipulations

Enhances generalization through domain-bridging and boundary-expanding features

Abstract

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.