Explicit Correlation Learning for Generalizable Cross-Modal Deepfake Detection

arXiv:2404.19171v1 Announce Type: new
Abstract: With the rising prevalence of deepfakes, there is a growing interest in developing generalizable detection methods for various types of deepfakes. While effective in their specific modalities, traditional detection methods fall short in addressing the generalizability of detection across diverse cross-modal deepfakes. This paper aims to explicitly learn potential cross-modal correlation to enhance deepfake detection towards various generation scenarios. Our approach introduces a correlation distillation task, which models the inherent cross-modal correlation based on content …

arxiv correlation cs.ai cs.cv deepfake detection modal type