MGAMNET: A Mask-Guided Attention Network for Deepfake Detection

Abstract

The rapid advancement of deepfake generation techniques poses increasing risks to security and privacy. Existing detection methods primarily focus on identifying artifacts in syn-thesized content, however these artifacts tend to be concentrated in specific facial regions, such as the eyes, mouth and facial boundaries. In this work, we introduce MGAMNET, a mask-guided attention network that enhances deepfake detection by in-tegrating face segmentation into the learning process. Our method utilizes segmentation-driven attention maps to guide the network toward the most informative facial regions, improving feature extraction and classification performance. Experimental results demonstrate that MGAMNET significantly enhances detection accuracy compared to baseline models, while also providing informative attention maps that highlight key facial areas.