Integrating Audio-Visual Features for Multimodal Deepfake Detection
This addresses privacy and security issues from AI-generated media, but it is incremental as it builds on existing multimodal detection without surpassing single-modality methods.
The paper tackles the problem of deepfake detection by proposing an audio-visual method that integrates fine-grained identification with binary classification, categorizing samples into four types based on single-modality labels to enhance detection in intra-domain and cross-domain testing.
Deepfakes are AI-generated media in which an image or video has been digitally modified. The advancements made in deepfake technology have led to privacy and security issues. Most deepfake detection techniques rely on the detection of a single modality. Existing methods for audio-visual detection do not always surpass that of the analysis based on single modalities. Therefore, this paper proposes an audio-visual-based method for deepfake detection, which integrates fine-grained deepfake identification with binary classification. We categorize the samples into four types by combining labels specific to each single modality. This method enhances the detection under intra-domain and cross-domain testing.