MSER-Net: Multi-stage edge refinement network for deepfake detection

• Extracting multi-scale edge information from feature maps to capture comprehensive and subtle forgery cues. • Perform feature interaction across multiple stages of the network and further refine edges. • Enhance features with multi-dimensional attention to highlight critical cues and achieve more effective feature fusion. Today, the malicious creation and dissemination of deepfake content has reached a level that threatens personal privacy and even social stability. To address this issue, many researchers have focused on deepfake detection tasks. However, many approaches rely solely on single spatial domain information, with training models directly extracting global artefacts from images for detection. Such approaches frequently lack accuracy and are vulnerable to interference. Meanwhile, forgery traces typically appear at the edges of tampered regions, and these subtle edge inconsistencies serve as effective cues for detecting deepfakes. To address these issues, we propose the multi-stage edge refinement network (MSER-Net), which uses VMamba as its backbone network and incorporates channel residual image (CRI) to detect unnatural colour anomalies introduced during the deepfake process. First, the designed multiscale edge enhancement module (MSEEM) processes low-level features from both branches, obtaining multi-scale edge information using the Sobel operator and highlighting subtle forgery traces. In addition, we use the detail-aware interaction module (DAIM) to extract complementary information from spatial and residual features, which improves edge artefacts. Finally, we propose the multidimensional attention fusion module (MAFM), which improves dual-branch features from multiple perspectives using the attention mechanism, resulting in more effective fusion. Experimental results on multiple public datasets show that our method outperforms state-of-the-art detection approaches and exhibits the best robustness against most post-processing attacks. The code is available at: https://github.com/ypzhang123/MSER-Net .