Safety
MSCT: Differential Cross-Modal Attention for Deepfake Detection
arXiv:2604.07741v1 Announce Type: new Abstract: Audio-visual deepfake detection typically employs a complementary multi-modal model to check the forgery traces in the video. These methods primarily ex
arXiv:2604.07741v1 Announce Type: new Abstract: Audio-visual deepfake detection typically employs a complementary multi-modal model to check the forgery traces in the video. These methods primarily extract forgery traces through audio-visual alignment, which results from the inconsistency between audio and video modalities. However, the traditional multi-modal forgery detection method has the problem of insufficient feature extraction and modal alignment deviation. To address this, we propose a multi-scale cross-modal transformer encoder (MSCT) for deepfake detection. Our approach includes a multi-scale self-attention to integrate the features of adjacent embeddings and a differential cross-modal attention to fuse multi-modal features. Our experiments demonstrate competitive performance on the FakeAVCeleb dataset, validating the effectiveness of the proposed structure.
Related
- Semantic Noise Reduction via Teacher-Guided Dual-Path Audio-Visual Representation Learning
- Faithful GRPO: Improving Visual Spatial Reasoning in Multimodal Language Models via Constrained Policy Optimization
- OpenVLThinkerV2: A Generalist Multimodal Reasoning Model for Multi-domain Visual Tasks
- Inside-Out: Measuring Generalization in Vision Transformers Through Inner Workings
Source: arXiv cs.CV | 2026-04-10