# MSCT: Differential Cross-Modal Attention for Deepfake Detection

arXiv: https://arxiv.org/abs/2604.07741 · HTML: https://mlsanity.com/paper/2604.07741/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 18 references that are in the map.
- First posted on arXiv 9 Apr 2026.

## Builds on (most cited first, 12 of 12)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Res2Net: A New Multi-scale Backbone Architecture](https://mlsanity.com/paper/1904.01169/) (2019)
- [FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset](https://mlsanity.com/paper/2108.05080/) (2021)
- [Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection](https://mlsanity.com/paper/2107.06592/) (2021)
- [Emotions Don't Lie: An Audio-Visual Deepfake Detection Method Using Affective Cues](https://mlsanity.com/paper/2003.06711/) (2020)
- [TALL: Thumbnail Layout for Deepfake Video Detection](https://mlsanity.com/paper/2307.07494/) (2023)
- [Not made for each other- Audio-Visual Dissonance-based Deepfake Detection and Localization](https://mlsanity.com/paper/2005.14405/) (2020)
- [Wavelet Convolutions for Large Receptive Fields](https://mlsanity.com/paper/2407.05848/) (2024)
- [Voice-Face Homogeneity Tells Deepfake](https://mlsanity.com/paper/2203.02195/) (2022)
- [BusterX: MLLM-Powered AI-Generated Video Forgery Detection and Explanation](https://mlsanity.com/paper/2505.12620/) (2025)
- [Cross-Modality and Within-Modality Regularization for Audio-Visual DeepFake Detection](https://mlsanity.com/paper/2401.05746/) (2024)

## Abstract (arXiv)

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.