Deepfake Forensics Adapter: A Dual-Stream Network for Generalizable Deepfake Detection

TL;DR

This paper introduces Deepfake Forensics Adapter (DFA), a dual-stream network combining vision-language models and forensics analysis to improve generalization in deepfake detection, achieving state-of-the-art results on benchmark datasets.

Contribution

The paper proposes a novel dual-stream framework integrating CLIP with forensics analysis, enhancing generalization and detection accuracy of deepfakes without modifying CLIP parameters.

Findings

Achieves state-of-the-art performance on DFDC dataset with high AUC and low EER.

Demonstrates superior generalization to unseen deepfake forgeries.

Outperforms previous methods with a 4.8% improvement in video-level AUC.

Abstract

The rapid advancement of deepfake generation techniques poses significant threats to public safety and causes societal harm through the creation of highly realistic synthetic facial media. While existing detection methods demonstrate limitations in generalizing to emerging forgery patterns, this paper presents Deepfake Forensics Adapter (DFA), a novel dual-stream framework that synergizes vision-language foundation models with targeted forensics analysis. Our approach integrates a pre-trained CLIP model with three core components to achieve specialized deepfake detection by leveraging the powerful general capabilities of CLIP without changing CLIP parameters: 1) A Global Feature Adapter is used to identify global inconsistencies in image content that may indicate forgery, 2) A Local Anomaly Stream enhances the model's ability to perceive local facial forgery cues by explicitly leveraging facial structure priors, and 3) An Interactive Fusion Classifier promotes deep interaction and fusion between global and local features using a transformer encoder. Extensive evaluations of frame-level and video-level benchmarks demonstrate the superior generalization capabilities of DFA, particularly achieving state-of-the-art performance in the challenging DFDC dataset with frame-level AUC/EER of 0.816/0.256 and video-level AUC/EER of 0.836/0.251, representing a 4.8% video AUC improvement over previous methods. Our framework not only demonstrates state-of-the-art performance, but also points out a feasible and effective direction for developing a robust deepfake detection system with enhanced generalization capabilities against the evolving deepfake threats. Our code is available at https://github.com/Liao330/DFA.git