# Self-supervised Transformer for Deepfake Detection

arXiv: https://arxiv.org/abs/2203.01265 · HTML: https://mlsanity.com/paper/2203.01265/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 48 references that are in the map.
- First posted on arXiv 2 Mar 2022.

## Builds on (most cited first, 30 of 39)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [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)
- [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)
- [How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)](https://mlsanity.com/paper/1703.07332/) (2017)
- [Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues](https://mlsanity.com/paper/2007.09355/) (2020)
- [Face X-ray for More General Face Forgery Detection](https://mlsanity.com/paper/1912.13458/) (2019)
- [MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation](https://mlsanity.com/paper/1903.01945/) (2019)
- [Multi-attentional Deepfake Detection](https://mlsanity.com/paper/2103.02406/) (2021)
- [FSGAN: Subject Agnostic Face Swapping and Reenactment](https://mlsanity.com/paper/1908.05932/) (2019)
- [Exposing DeepFake Videos By Detecting Face Warping Artifacts](https://mlsanity.com/paper/1811.00656/) (2018)
- [Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detection](https://mlsanity.com/paper/2012.07657/) (2020)
- [What makes fake images detectable? Understanding properties that generalize](https://mlsanity.com/paper/2008.10588/) (2020)
- [Deep Video Portraits](https://mlsanity.com/paper/1805.11714/) (2018)
- [DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection](https://mlsanity.com/paper/2001.03024/) (2020)
- [Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domain](https://mlsanity.com/paper/2103.01856/) (2021)
- [SimSwap: An Efficient Framework For High Fidelity Face Swapping](https://mlsanity.com/paper/2106.06340/) (2021)
- [A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning](https://mlsanity.com/paper/2104.14558/) (2021)
- [Audio-Visual Instance Discrimination with Cross-Modal Agreement](https://mlsanity.com/paper/2004.12943/) (2020)
- [RetinaFace: Single-stage Dense Face Localisation in the Wild](https://mlsanity.com/paper/1905.00641/) (2019)
- [Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation](https://mlsanity.com/paper/1804.03619/) (2018)
- [Two-branch Recurrent Network for Isolating Deepfakes in Videos](https://mlsanity.com/paper/2008.03412/) (2020)
- [VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples](https://mlsanity.com/paper/2103.05905/) (2021)
- [TCLR: Temporal Contrastive Learning for Video Representation](https://mlsanity.com/paper/2101.07974/) (2021)
- [Multi-task Learning For Detecting and Segmenting Manipulated Facial Images and Videos](https://mlsanity.com/paper/1906.06876/) (2019)

## Built on by (most cited first, 22 of 22)

- [TALL: Thumbnail Layout for Deepfake Video Detection](https://mlsanity.com/paper/2307.07494/) (2023)
- [Beyond the Prior Forgery Knowledge: Mining Critical Clues for General Face Forgery Detection](https://mlsanity.com/paper/2304.12489/) (2023)
- [SepMark: Deep Separable Watermarking for Unified Source Tracing and Deepfake Detection](https://mlsanity.com/paper/2305.06321/) (2023)
- [Learning Natural Consistency Representation for Face Forgery Video Detection](https://mlsanity.com/paper/2407.10550/) (2024)
- [FSFM: A Generalizable Face Security Foundation Model via Self-Supervised Facial Representation Learning](https://mlsanity.com/paper/2412.12032/) (2024)
- [Learning Spatiotemporal Inconsistency via Thumbnail Layout for Face Deepfake Detection](https://mlsanity.com/paper/2403.10261/) (2024)
- [Hierarchical Forgery Classifier On Multi-modality Face Forgery Clues](https://mlsanity.com/paper/2212.14629/) (2022)
- [AVTENet: A Human-Cognition-Inspired Audio-Visual Transformer-Based Ensemble Network for Video Deepfake Detection](https://mlsanity.com/paper/2310.13103/) (2023)
- [SpeechForensics: Audio-Visual Speech Representation Learning for Face Forgery Detection](https://mlsanity.com/paper/2508.09913/) (2025)
- [Self-Supervised Graph Transformer for Deepfake Detection](https://mlsanity.com/paper/2307.15019/) (2023)
- [Unmasking Deepfakes: Masked Autoencoding Spatiotemporal Transformers for Enhanced Video Forgery Detection](https://mlsanity.com/paper/2306.06881/) (2023)
- [NPVForensics: Jointing Non-critical Phonemes and Visemes for Deepfake Detection](https://mlsanity.com/paper/2306.06885/) (2023)
- [Passive Deepfake Detection Across Multi-modalities: A Comprehensive Survey](https://mlsanity.com/paper/2411.17911/) (2024)
- [Face2Parts: Exploring Coarse-to-Fine Inter-Regional Facial Dependencies for Generalized Deepfake Detection](https://mlsanity.com/paper/2603.26036/) (2026)
- [WWW: Where, Which and Whatever Enhancing Interpretability in Multimodal Deepfake Detection](https://mlsanity.com/paper/2408.02954/) (2024)
- [Unearthing Common Inconsistency for Generalisable Deepfake Detection](https://mlsanity.com/paper/2311.11549/) (2023)
- [Lightweight Joint Audio-Visual Deepfake Detection via Single-Stream Multi-Modal Learning Framework](https://mlsanity.com/paper/2506.07358/) (2025)
- [Investigating self-supervised representations for audio-visual deepfake detection](https://mlsanity.com/paper/2511.17181/) (2025)
- [Latent Spatiotemporal Adaptation for Generalized Face Forgery Video Detection](https://mlsanity.com/paper/2309.04795/) (2023)
- [Code and Pixels: Multi-Modal Contrastive Pre-training for Enhanced Tabular Data Analysis](https://mlsanity.com/paper/2501.07304/) (2025)
- [LAA-X: Unified Localized Artifact Attention for Quality-Agnostic and Generalizable Face Forgery Detection](https://mlsanity.com/paper/2604.04086/) (2026)
- [Attribution-Guided Multimodal Deepfake Detection via Cross-Modal Forensic Fingerprints](https://mlsanity.com/paper/2604.26453/) (2026)

## Abstract (arXiv)

The fast evolution and widespread of deepfake techniques in real-world scenarios require stronger generalization abilities of face forgery detectors. Some works capture the features that are unrelated to method-specific artifacts, such as clues of blending boundary, accumulated up-sampling, to strengthen the generalization ability. However, the effectiveness of these methods can be easily corrupted by post-processing operations such as compression. Inspired by transfer learning, neural networks pre-trained on other large-scale face-related tasks may provide useful features for deepfake detection. For example, lip movement has been proved to be a kind of robust and good-transferring highlevel semantic feature, which can be learned from the lipreading task. However, the existing method pre-trains the lip feature extraction model in a supervised manner, which requires plenty of human resources in data annotation and increases the difficulty of obtaining training data. In this paper, we propose a self-supervised transformer based audio-visual contrastive learning method. The proposed method learns mouth motion representations by encouraging the paired video and audio representations to be close while unpaired ones to be diverse. After pre-training with our method, the model will then be partially fine-tuned for deepfake detection task. Extensive experiments show that our self-supervised method performs comparably or even better than the supervised pre-training counterpart.