Deepfake Detection: A Comparative Analysis
Not on the map. Why?
Abstract (arXiv)
This paper present a comprehensive comparative analysis of supervised and self-supervised models for deepfake detection. We evaluate eight supervised deep learning architectures and two transformer-based models pre-trained using self-supervised strategies (DINO, CLIP) on four benchmarks (FakeAVCeleb, CelebDF-V2, DFDC, and FaceForensics++). Our analysis includes intra-dataset and inter-dataset evaluations, examining the best performing models, generalisation capabilities, and impact of augmentations. We also investigate the trade-off between model size and performance. Our main goal is to provide insights into the effectiveness of different deep learning architectures (transformers, CNNs), training strategies (supervised, self-supervised), and deepfake detection benchmarks. These insights can help guide the development of more accurate and reliable deepfake detection systems, which are crucial in mitigating the harmful impact of deepfakes on individuals and society.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 35 of its 47 references that are in the map. First posted on arXiv 7 Aug 2023.
Builds on
35 of 47 references.
References · 35
- 2017Attention Is All You Needcited by 59,932
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
- 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
- 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
- 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
- 2014Going Deeper with Convolutionscited by 4,231
- 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
- 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
- 2021Is Space-Time Attention All You Need for Video Understanding?cited by 1,609
23 more
- 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,095
- 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 916
- 2021Multiscale Vision Transformerscited by 896
- 2020A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wildcited by 669
- 2020Face2Face: Real-time Face Capture and Reenactment of RGB Videoscited by 631
- 2019Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensicscited by 573
- 2019Res2Net: A New Multi-scale Backbone Architecturecited by 468
- 2017Deep Layer Aggregationcited by 436
- 2018MesoNet: a Compact Facial Video Forgery Detection Networkcited by 409
- 2019FSGAN: Subject Agnostic Face Swapping and Reenactmentcited by 319
- 2019Few-Shot Adversarial Learning of Realistic Neural Talking Head Modelscited by 284
- 2018Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesiscited by 280
- 2018Capsule-Forensics: Using Capsule Networks to Detect Forged Images and Videoscited by 180
- 2021FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Datasetcited by 179
- 2017Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognitioncited by 178
- 2019FakeCatcher: Detection of Synthetic Portrait Videos using Biological Signalscited by 143
- 2016Fast Face-swap Using Convolutional Neural Networkscited by 119
- 2019Recurrent Convolutional Strategies for Face Manipulation Detection in Videoscited by 118
- 2021M2TR: Multi-modal Multi-scale Transformers for Deepfake Detectioncited by 114
- 2021Combining EfficientNet and Vision Transformers for Video Deepfake Detectioncited by 81
- 2020Face Forgery Detection by 3D Decompositioncited by 53
- 2021Video Transformer for Deepfake Detection with Incremental Learningcited by 33
- 2018Big-Little Net: An Efficient Multi-Scale Feature Representation for Visual and Speech Recognitioncited by 22
Built on by
Citing papers per year: 2024: 1; 2025: 0; 2026: 1.
2 papers.