# Multiscale Adaptive Conflict-Balancing Model For Multimedia Deepfake Detection

arXiv: https://arxiv.org/abs/2505.12966 · HTML: https://mlsanity.com/paper/2505.12966/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 49 references that are in the map.
- First posted on arXiv 19 May 2025.

## Builds on (most cited first, 19 of 19)

- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [What Makes Training Multi-Modal Classification Networks Hard?](https://mlsanity.com/paper/1905.12681/) (2019)
- [Multi-attentional Deepfake Detection](https://mlsanity.com/paper/2103.02406/) (2021)
- [Everybody Dance Now](https://mlsanity.com/paper/1808.07371/) (2018)
- [Balanced Multimodal Learning via On-the-fly Gradient Modulation](https://mlsanity.com/paper/2203.15332/) (2022)
- [RUBi: Reducing Unimodal Biases in Visual Question Answering](https://mlsanity.com/paper/1906.10169/) (2019)
- [Capsule-Forensics: Using Capsule Networks to Detect Forged Images and Videos](https://mlsanity.com/paper/1810.11215/) (2018)
- [Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection](https://mlsanity.com/paper/2203.12208/) (2022)
- [FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis](https://mlsanity.com/paper/2204.09934/) (2022)
- [Emotions Don't Lie: An Audio-Visual Deepfake Detection Method Using Affective Cues](https://mlsanity.com/paper/2003.06711/) (2020)
- [Not made for each other- Audio-Visual Dissonance-based Deepfake Detection and Localization](https://mlsanity.com/paper/2005.14405/) (2020)
- [Face Forensics in the Wild](https://mlsanity.com/paper/2103.16076/) (2021)
- [Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems](https://mlsanity.com/paper/1812.08305/) (2018)
- [Exploiting Fine-grained Face Forgery Clues via Progressive Enhancement Learning](https://mlsanity.com/paper/2112.13977/) (2021)
- [VASparse: Towards Efficient Visual Hallucination Mitigation via Visual-Aware Token Sparsification](https://mlsanity.com/paper/2501.06553/) (2025)
- [Do we really have to filter out random noise in pre-training data for language models?](https://mlsanity.com/paper/2502.06604/) (2025)
- [Imbalanced Open Set Domain Adaptation via Moving-threshold Estimation and Gradual Alignment](https://mlsanity.com/paper/2303.04393/) (2023)
- [ATRI: Mitigating Multilingual Audio Text Retrieval Inconsistencies by Reducing Data Distribution Errors](https://mlsanity.com/paper/2502.14627/) (2025)
- [Exploiting Human Social Cognition for the Detection of Fake and Fraudulent Faces via Memory Networks](https://mlsanity.com/paper/1911.07844/) (2019)

## Abstract (arXiv)

Advances in computer vision and deep learning have blurred the line between deepfakes and authentic media, undermining multimedia credibility through audio-visual forgery. Current multimodal detection methods remain limited by unbalanced learning between modalities. To tackle this issue, we propose an Audio-Visual Joint Learning Method (MACB-DF) to better mitigate modality conflicts and neglect by leveraging contrastive learning to assist in multi-level and cross-modal fusion, thereby fully balancing and exploiting information from each modality. Additionally, we designed an orthogonalization-multimodal pareto module that preserves unimodal information while addressing gradient conflicts in audio-video encoders caused by differing optimization targets of the loss functions. Extensive experiments and ablation studies conducted on mainstream deepfake datasets demonstrate consistent performance gains of our model across key evaluation metrics, achieving an average accuracy of 95.5% across multiple datasets. Notably, our method exhibits superior cross-dataset generalization capabilities, with absolute improvements of 8.0% and 7.7% in ACC scores over the previous best-performing approach when trained on DFDC and tested on DefakeAVMiT and FakeAVCeleb datasets.