Improved Deepfake Video Detection Using Convolutional Vision Transformer
Open accessAbstract
Deepfakes are hyper-realistic videos in which the faces are replaced, swapped, or forged using deep-learning models. This potent media manipulation techniques hold promise for applications across various domains. Yet, they also present a significant risk when employed for malicious intents like iden-tity fraud, phishing, spreading false information, and executing scams. In this work, we propose a novel and improved Deepfake video detector that uses a Convolutional Vision Transformer (CViT2), which builds on the concepts of our previous work (CViT). The CViT architecture consists of two components: a Convolutional Neural Network that extracts learnable features, and a Vision Transformer that categorizes these learned features using an attention mechanism. We trained and evaluted our model on 5 datasets, namely Deepfake Detection Challenge Dataset (DFDC),$\mathbf{FaceForensics++} \ (\text{FF}++)$I, Celeb-DF v2, Deep-fakeTIMIT, and TrustedMedia. On the test sets unseen during training, we achieved an accuracy of 95 %, 94.8 %, 98.3 % and 76.7% on the DFDC,$\mathbf{FF ++}$, Celeb-DF v2, and TIMIT datasets, respectively. In conclusion, our proposed Deepfake detector can be used in the battle against misinformation and other forensic use cases.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
DFDC deepfake videos may contain pristine frames, and face regions may not always be accurately detected by face recognition frameworks, leading to some frames in the training dataset containing no faces.
“As noted in [74], (1) DFDC deepfake videos may contain pristine frames and (2) face regions may not always be accurately detected by the face recognition frameworks used to extract them, leading to some frames in the training dataset containing no faces [60].”
From GenConViT: Deepfake Video Detection Using Generative Convolutional Vision Transformer (2025) · cites this paper as [60]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
The publisher hasn’t deposited this paper’s reference list.
Research works printed but not linked: 26
- D. Afchar, V. Nozick, J. Yamagishi, and I. Echizen, "MesoNet: a Compact Facial Video Forgery Detection Network," in Proc. IEEE WIFS 2018, 2018, pp. 1-7.
- L. Zheng, Y. Zhang, and V. L. Thing, "A survey on image tampering and its detection in real-world photos," Elsevier, vol. 58, pp. 380-399, 2018.
- A. J. Bose and P. Aarabi, "Virtual Fakes: DeepFakes for Virtual Reality," in Proc. IEEE MMSP 2019. IEEE, 2019, pp. 1-1.
- K. Yao, J. Wang, B. Diao, and C. Li, "Towards under- standing the generalization of deepfake detectors from a game-theoretical view." IEEE, 2023.
- H. Mareen, L. De Neve, P. Lambert, and G. Van Wallen- dael, "Harmonizing image forgery detection & localiza- tion: Fusion of complementary approaches," Journal of Imaging, vol. 10, no. 1, 2024.
- J. Brockschmidt, J. Shang, and J. Wu, "On the Generality of Facial Forgery Detection," in Proc. IEEE MASSW 2019. IEEE, 2019, pp. 43-47.
- C. Sanderson and B. C. Lovell, "Multi-region probabilis- tic histograms for robust and scalable identity inference," in Advances in Biometrics, M. Tistarelli and M. S. Nixon, Eds. Berlin, Heidelberg: Springer Berlin Heidelberg, 2009, pp. 199-208.
- A. Khodabakhsh, R. Ramachandra, K. Raja, and P. Was- nik, "Fake face detection methods: Can they be general- ized?" in Proc. BIOSIG 2018. IEEE, 2018, pp. 1-6.
- Y. Nirkin, Y. Keller, and T. Hassner, "FSGAN: Subject Agnostic Face Swapping and Reenactment," in Proc. IEEE/CVF ICCV 2019. IEEE, 2019, pp. 7183-7192.
- S. Suwajanakorn, S. M. Seitz, and I. Kemelmacher- Shlizerman, "Synthesizing Obama: Learning Lip Sync from Audio," ACM Trans. Graph., vol. 36, no. 4, pp. 780-789, 2017.
- K. R. Prajwal, R. Mukhopadhyay, J. Philip, A. Jha, V. P. Namboodiri, and C. V. Jawahar, "Towards Automatic Face-to-Face Translation," in Proc. 27th ACM Int. Conf. on Multimedia (MM '19). New York, NY, USA: Asso- ciation for Computing Machinery, 2019, p. 1428-1436.
- S. D. et al., "A Review on Face Reenactment Tech- niques," in Proc. 2020 Int. Conf. on Industry 4.0 Tech- nology (I4Tech). Pune, India: IEEE, 2020, pp. 191-194.
- R. Tolosana, R. Vera-Rodriguez, J. Fierrez, A. Morales, and J. Ortega-Garcia, "DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection," Inf. Fusion, vol. 64, pp. 131-148, 2020.
- Y. Mirsky and W. Lee, "The Creation and Detection of Deepfakes: A Survey," ACM Comput. Surv., vol. 54, no. 1, 2021.
- B. Martinez, M. F. Valstar, B. Jiang, and M. Pantic, "Automatic Analysis of Facial Actions: A Survey," IEEE Transactions on Affective Computing, vol. 10, no. 3, pp. 325-347, 2019.
- P. Charitidis, G. Kordopatis-Zilos, S. Papadopoulos, and I. Kompatsiaris, "DeepVision: Deepfakes Detection Us- ing Human Eye Blinking Pattern," IEEE Access, vol. 8, pp. 83 144-83 154, 2020.
- K. Vougioukas, S. Petridis, and M. Pantic, "Realistic Speech-Driven Facial Animation with GANs," Int. J. Comput. Vis., vol. 128, p. 1398-1413, 2020.
- H. H. Nguyen, N.-D. T. Tieu, H.-Q. Nguyen-Son, V. Noz- ick, J. Yamagishi, and I. Echizen, "Modular Convo- lutional Neural Network for Discriminating between Computer-Generated Images and Photographic Images," in Proc. 13th Int. Conf. on Availability, Reliability and Security. New York, NY, USA: Commun. ACM, 2018.
- J. Thies, M. Zollhöfer, M. Stamminger, C. Theobalt, and M. Nießner, "Face2Face: Real-Time Face Capture and Reenactment of RGB Videos," Commun. ACM, vol. 62, no. 1, p. 96-104, 2018.
- D. M. Montserrat, H. Hao, S. K. Yarlagadda, S. Baireddy, R. Shao, J. Horvath, E. Bartusiak, J. Yang, D. Guera, F. Zhu, and E. J. Delp, "Deepfakes Detection with Auto- matic Face Weighting," in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2020, pp. 2851-2859.
- J. Kim, S. Han, and S. S. Woo, "Classifying Genuine Face images from Disguised Face Images," in Proc. 2019 IEEE Int. Conf. on Big Data (Big Data), 2019, pp. 6248- 6250.
- A. Krizhevsky, I. Sutskever, and G. E. Hinton, "Im- ageNet Classification with Deep Convolutional Neural Networks," Commun. ACM, vol. 60, no. 6, p. 84-90, 2017.
- K. He, X. Zhang, S. Ren, and J. Sun, "Deep Residual Learning for Image Recognition," in Proc. CVPR. IEEE, 2016, pp. 770-778.
- K. Simonyan and A. Zisserman, "Very Deep Convolu- tional Networks for Large-Scale Image Recognition," in Proc. of ICLR 2015, Conference Track, Y. Bengio and Y. LeCun, Eds., 2015.
- A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, "Attention is All You Need," in Proceedings of the 31st International Conference on Neural Information Processing Systems, ser. NIPS'17. Curran Associates Inc., 2017, p. 6000-6010.
- A. P. Bradley, "The use of the area under the ROC curve in the evaluation of machine learning algorithms," Pattern Recognition, vol. 30, no. 7, pp. 1145-1159, 1997.
Cited by
Sorted by citations
GenConViT: Deepfake Video Detection Using Generative Convolutional Vision Transformer
Deressa, D. W., Mareen, H., Lambert, P., Atnafu, S., Akhtar, Z., & Van Wallendael, G. (2025) · Applied Sciences · doi:10.3390/app15126622 · Cited by 46 · see citing works
Self-citationA Deepfake Image Detection Method Based on a Multi-Graph Attention Network
Chen, G., Du, C., Yuan, Y., Hu, H. G., Duan, H., & Zhu, H. (2025) · Electronics · doi:10.3390/electronics14030482 · Cited by 15 · see citing works
Katı, B. E., Küçüksille, E. U., & Sarıman, G. (2025) · Applied Sciences · doi:10.3390/app15020525 · Cited by 12 · see citing works
MesoNet-ViT: Meso Network and Vision Transformer for Deepfake Detection
İlhan, İ., & Karaköse, M. (2025) · doi:10.1109/it64745.2025.10930249 · Cited by 8 · see citing works
Cross-dataset video deepfake detection using Transformer and CNN architectures
Petmezas, G. (2026) · Machine Vision and Applications · doi:10.1007/s00138-026-01809-w · Cited by 6 · see citing works
ResNeXt-50 and LSTM for Deepfake Detection
Kamil, F., Maharani, E. M., & Rahmania, R. (2025) · IEEE International Conference on Artificial Intelligence for Learning and Optimization (ICoAILO) · doi:10.1109/icoailo66760.2025.11156046 · Cited by 3 · see citing works
A DeepFake Face Detection Method Using Vision Transformer with a Convolutional Module
Liu, D., & Lin, Y. (2024) · International Conference on Advanced Computer Theory and Engineering · doi:10.1109/icacte62428.2024.10871782 · Cited by 3 · see citing works
Hierarchical Multi-Branch Deepfake Detection Network (HMBDDN)
Mohammadi, A. M., & Ratha, N. (2024) · IEEE Western New York Image and Signal Processing Workshop (WNYISPW) · doi:10.1109/wnyispw63690.2024.10786607 · Cited by 1 · see citing works
Mohamed, K. M., Skaiky, A. A., Ali, H. M. S., Mohammed, A., & Mahdi, Z. A. (2025) · IEEE International Conference on Computing and Machine Intelligence (ICMI) · doi:10.1109/icmi65310.2025.11141060 · Cited by 1 · see citing works
Alshahrani, M. H., Maashi, M. S., & Benabid, A. (2025) · IEEE Access · doi:10.1109/access.2025.3625266 · Cited by 1 · see citing works
STDD: A Hybrid Spatial-Temporal model for Deepfake Detection
Pham, T. M., Bui, L. T., Tran, H. V., & Pham, T. D. (2025) · doi:10.1145/3709020.3734831
(2025) · International journal of intelligent engineering and systems · doi:10.22266/ijies2025.0930.29
Bermúdez, Y. A. B. (2025) · IUSTA · doi:10.15332/25005286.11068
Spatiotemporal and Behavioral Feature-Aware Model with XceptionCapsule Fusion for Deepfake Detection
Rajeev, A., & Raviraj, P. (2026) · Informatics and Automation · doi:10.15622/ia.25.1.4
Improving Deepfake Detection Using Sparse Google Net
Koravi, P., Phursule, R. N., & Sapate, S. G. (2025) · IEEE International Conference on Blockchain and Distributed Systems Security (ICBDS) · doi:10.1109/icbds67396.2025.11377717
Unified Face Attack Detection Via Multi-Scale CNN-ViT and Graph Convolutional Networks
Chen, X., Liu, J., Huang, Z., & Zhang, D. (2025) · International Conference on Pattern Recognition and Artificial Intelligence (PRAI) · doi:10.1109/prai67447.2025.11412603
Truth Lens: A Deep Learning System to Detect Fake News Videos
Sayed, A., Surti, N., Vengurlekar, O., Pandey, P., Yadav, B., & Raut, A. (2026) · International Conference on Communication, Computing and Emerging Technologies (IC3ET) · doi:10.1109/ic3et64989.2026.11467317
Robust deepfake video detection using spatio-temporal features and dynamic difference learning
AbdElfattah, E., Mousa, H. M., El-Sisi, A. B., & Mahmoud, N. (2026) · Scientific Reports · doi:10.1038/s41598-026-53545-w
Akshatha, G. C., Shastry, K. A., Prasad, K., & L, D. G. (2026) · International Journal of Computational Intelligence and Applications · doi:10.1142/s1469026826500264
A Hybrid Quantum Deep Learning Framework With QNN and DenseNet121 for Deepfake Detection
Jasmine, S., Abirami, N., Varalakshmi, I., & Hamdani, M. A. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-8292-0.ch001
A Hybrid Xception-ViT Architecture for Enhanced Deepfake Video Detection
Huang, P., Lin, P., Odle, E., & Arbaiy, N. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-25638-6_20
Development of Convolutional Vision Transformer for Detection of Deepfake Video
Dhanabal, S., M.Deepadharshini, Subhash, V. V., & Karthic, B. S. M. (2026) · doi:10.1109/icstem68144.2026.11735518
- Authors
- Deressa, D. W., Lambert, P., Van Wallendael, G., Atnafu, S., & Mareen, H.
- Affiliations
- Ghent University - imec, IDLab,Department of Electronics and Information Systems,Gent,Belgium
- Ghent University (BE)
- Addis Ababa University (ET)
- Venue
- 2024 IEEE Gaming, Entertainment, and Media Conference (GEM)
- Publisher
- IEEE
- Published
- 2024-06-05
- Pages
- 1-6
- OpenAlex
- W4400526883
- Cited by
- 20
- References
- 0
- Citations by year
- 2026: 7 · 2025: 11 · 2024: 2
- FWCI
- 4.14
- Type
- conference paper
- Language
- en
- Open access
- green
- biblio.ugent.be
- Locations
- IEEE Gaming, Entertainment, and Media Conference (GEM) (publishedVersion)
- Ghent University Academic Bibliography (Ghent University) (submittedVersion, other-oa)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
- Keywords
- deepfake detection, video forgery, convolutional vision transformer, face swapping, media manipulation, misinformation, attention mechanism, DFDC, FaceForensics++, Celeb-DF, identity fraud
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
