Selective Domain-Invariant Feature for Generalizable Deepfake Detection
This work addresses the challenge of generalizable deepfake detection for security and media verification, representing an incremental improvement over existing methods.
The paper tackles the problem of poor generalizability in deepfake detection across unseen domains by proposing the Selective Domain-Invariant Feature (SDIF) framework, which fuses content and style features to reduce sensitivity to forgery, achieving improved performance as demonstrated in benchmarks.
With diverse presentation forgery methods emerging continually, detecting the authenticity of images has drawn growing attention. Although existing methods have achieved impressive accuracy in training dataset detection, they still perform poorly in the unseen domain and suffer from forgery of irrelevant information such as background and identity, affecting generalizability. To solve this problem, we proposed a novel framework Selective Domain-Invariant Feature (SDIF), which reduces the sensitivity to face forgery by fusing content features and styles. Specifically, we first use a Farthest-Point Sampling (FPS) training strategy to construct a task-relevant style sample representation space for fusing with content features. Then, we propose a dynamic feature extraction module to generate features with diverse styles to improve the performance and effectiveness of the feature extractor. Finally, a domain separation strategy is used to retain domain-related features to help distinguish between real and fake faces. Both qualitative and quantitative results in existing benchmarks and proposals demonstrate the effectiveness of our approach.