# Cross-modal Translation via Conditional Latent Denoising for Video Deepfake Detection

arXiv: https://arxiv.org/abs/2609.33394 · HTML: https://mlsanity.com/paper/2609.33394/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 20 references that are in the map.
- First posted on arXiv 27 Sep 2026.

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

- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detection](https://mlsanity.com/paper/2012.07657/) (2020)
- [FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset](https://mlsanity.com/paper/2108.05080/) (2021)
- [Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection](https://mlsanity.com/paper/2201.07131/) (2022)
- [AVFF: Audio-Visual Feature Fusion for Video Deepfake Detection](https://mlsanity.com/paper/2406.02951/) (2024)
- [Voice-Face Homogeneity Tells Deepfake](https://mlsanity.com/paper/2203.02195/) (2022)
- [Cross-Modality and Within-Modality Regularization for Audio-Visual DeepFake Detection](https://mlsanity.com/paper/2401.05746/) (2024)
- [AVT2-DWF: Improving Deepfake Detection with Audio-Visual Fusion and Dynamic Weighting Strategies](https://mlsanity.com/paper/2403.14974/) (2024)
- [Next-Frame Feature Prediction for Multimodal Deepfake Detection and Temporal Localization](https://mlsanity.com/paper/2511.10212/) (2025)

## Abstract (arXiv)

The growing threat of video deepfakes necessitates multimodal detection. Beyond serving as independent indicators of authenticity, audio and visual signals have intrinsic dependencies that also provide an essential criterion for detection. Previous methods often overlook the cross-modal correspondences, hindering information transfer between domains and leaving crucial detection cues unexplored. To address this challenge, we propose a framework called Cross-modal Translation via Conditional Latent Denoising (CTCLD) for video deepfake detection. It connects the distinct distributions of heterogeneous modalities in latent spaces, enabling smooth cross-domain information transfer to improve detection performance. We first establish a Bayesian foundation by decomposing the audio-visual joint distribution. Subsequently, CTCLD translates both modalities via bidirectional latent denoising conditioned on each other, effectively capturing subtle inconsistencies in the manipulated signals. Experimental results demonstrate that the proposed CTCLD enables comprehensive domain alignment, resulting in a robust video deepfake detection approach with competitive performance.