# Lightweight Joint Audio-Visual Deepfake Detection via Single-Stream Multi-Modal Learning Framework

arXiv: https://arxiv.org/abs/2506.07358 · HTML: https://mlsanity.com/paper/2506.07358/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 43 references that are in the map.
- First posted on arXiv 9 Jun 2025.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics](https://mlsanity.com/paper/1909.12962/) (2019)
- [Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech](https://mlsanity.com/paper/2106.06103/) (2021)
- [Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detection](https://mlsanity.com/paper/2012.07657/) (2020)
- [DeepFakes: a New Threat to Face Recognition? Assessment and Detection](https://mlsanity.com/paper/1812.08685/) (2018)
- [FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset](https://mlsanity.com/paper/2108.05080/) (2021)
- [Learning Self-Consistency for Deepfake Detection](https://mlsanity.com/paper/2012.09311/) (2020)
- [S3FD: Single Shot Scale-invariant Face Detector](https://mlsanity.com/paper/1708.05237/) (2017)
- [Emotions Don't Lie: An Audio-Visual Deepfake Detection Method Using Affective Cues](https://mlsanity.com/paper/2003.06711/) (2020)
- [Protecting Celebrities from DeepFake with Identity Consistency Transformer](https://mlsanity.com/paper/2203.01318/) (2022)
- [Not made for each other- Audio-Visual Dissonance-based Deepfake Detection and Localization](https://mlsanity.com/paper/2005.14405/) (2020)
- [KoDF: A Large-scale Korean DeepFake Detection Dataset](https://mlsanity.com/paper/2103.10094/) (2021)
- [WaveFake: A Data Set to Facilitate Audio Deepfake Detection](https://mlsanity.com/paper/2111.02813/) (2021)
- [BiHPF: Bilateral High-Pass Filters for Robust Deepfake Detection](https://mlsanity.com/paper/2109.00911/) (2021)
- [DeepFake Detection: Current Challenges and Next Steps](https://mlsanity.com/paper/2003.09234/) (2020)
- [Audio-Visual Person-of-Interest DeepFake Detection](https://mlsanity.com/paper/2204.03083/) (2022)
- [Cross-Modality and Within-Modality Regularization for Audio-Visual DeepFake Detection](https://mlsanity.com/paper/2401.05746/) (2024)
- [Self-supervised Transformer for Deepfake Detection](https://mlsanity.com/paper/2203.01265/) (2022)
- [Attention-Based Lip Audio-Visual Synthesis for Talking Face Generation in the Wild](https://mlsanity.com/paper/2203.03984/) (2022)
- [DeepFake MNIST+: A DeepFake Facial Animation Dataset](https://mlsanity.com/paper/2108.07949/) (2021)

## Built on by (most cited first, 1 of 1)

- [Teacher-Student Structure for Domain Adaptation in Ensemble Audio-Visual Video Deepfake Detection](https://mlsanity.com/paper/2606.15117/) (2026)

## Abstract (arXiv)

Deepfakes are AI-synthesized multimedia data that may be abused for spreading misinformation. Deepfake generation involves both visual and audio manipulation. To detect audio-visual deepfakes, previous studies commonly employ two relatively independent sub-models to learn audio and visual features, respectively, and fuse them subsequently for deepfake detection. However, this may underutilize the inherent correlations between audio and visual features. Moreover, utilizing two isolated feature learning sub-models can result in redundant neural layers, making the overall model inefficient and impractical for resource-constrained environments. In this work, we design a lightweight network for audio-visual deepfake detection via a single-stream multi-modal learning framework. Specifically, we introduce a collaborative audio-visual learning block to efficiently integrate multi-modal information while learning the visual and audio features. By iteratively employing this block, our single-stream network achieves a continuous fusion of multi-modal features across its layers. Thus, our network efficiently captures visual and audio features without the need for excessive block stacking, resulting in a lightweight network design. Furthermore, we propose a multi-modal classification module that can boost the dependence of the visual and audio classifiers on modality content. It also enhances the whole resistance of the video classifier against the mismatches between audio and visual modalities. We conduct experiments on the DF-TIMIT, FakeAVCeleb, and DFDC benchmark datasets. Compared to state-of-the-art audio-visual joint detection methods, our method is significantly lightweight with only 0.48M parameters, yet it achieves superiority in both uni-modal and multi-modal deepfakes, as well as in unseen types of deepfakes.