Evaluation of an Audio-Video Multimodal Deepfake Dataset using Unimodal and Multimodal Detectors
Open accessThe DOI matches its Crossref record; 84 of the 84 references it cites were found in a registry or an index.
Abstract
Significant advancements made in the generation of deepfakes have caused security and privacy issues. Attackers can easily impersonate a person's identity in an image by replacing his face with the target person's face. Moreover, a new domain of cloning human voices using deep-learning technologies is also emerging. Now, an attacker can generate realistic cloned voices of humans using only a few seconds of audio of the target person. With the emerging threat of potential harm deepfakes can cause, researchers have proposed deepfake detection methods. However, they only focus on detecting a single modality, i.e., either video or audio. On the other hand, to develop a good deepfake detector that can cope with the recent advancements in deepfake generation, we need to have a detector that can detect deepfakes of multiple modalities, i.e., videos and audios. To build such a detector, we need a dataset that contains video and respective audio deepfakes. We were able to find a most recent deepfake dataset, Audio-Video Multimodal Deepfake Detection Dataset (FakeAVCeleb), that contains not only deepfake videos but synthesized fake audios as well. We used this multimodal deepfake dataset and performed detailed baseline experiments using state-of-the-art unimodal, ensemble-based, and multimodal detection methods to evaluate it. We conclude through detailed experimentation that unimodals, addressing only a single modality, video or audio, do not perform well compared to ensemble-based methods. Whereas purely multimodal-based baselines provide the worst performance.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“This may confuse the feature learning of a single modality, especially in ensemble-based fusion [9, 11, 15].”
From Integrating Audio-Visual Features For Multimodal Deepfake Detection (2023) · cites this paper as [11]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“However, existing feature fusion methods treat different types of deepfakes as the same fake type.”
From Integrating Audio-Visual Features For Multimodal Deepfake Detection (2023) · cites this paper as [11]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Moreover, the results of [38] show that an ensemble of audio and visual baselines outperforms monomodal counterparts.”
From A Robust Approach to Multimodal Deepfake Detection (2023) · cites this paper as [38]
The cited source says what the claim attributes to it.
In the citing paper
“Existing methods for audio-visual detection do not always surpass that of the analysis based on single modalities.”
From Integrating Audio-Visual Features For Multimodal Deepfake Detection (2023) · cites this paper as [11]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
Rethinking the Inception Architecture for Computer Vision
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.308 · Cited by 32,138
Xception: Deep Learning with Depthwise Separable Convolutions
Chollet, F. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.195 · Cited by 20,380
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
Tan, M., & Le, Q. V. (2019) · arXiv · doi:10.48550/arxiv.1905.11946 · Cited by 17,072
Estimating the Support of a High-Dimensional Distribution
Schölkopf, B., Platt, J. C., Shawe-Taylor, J., Smola, A. J., & Williamson, R. C. (2001) · Neural Computation · doi:10.1162/089976601750264965 · Cited by 6,168 · cited 1×
“Some of the most recent methods include detection based on splice detection in which they try to exploit the inconsistencies that arise from splicing near the boundaries of manipulated areas in an image [6, 94, 95] abnormal eye-blinking [38], one-class classification [27, 54, 65], irregular head poses [91] andmany oth…”
MethodGenerative Adversarial Networks
Goodfellow, I. J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1406.2661 · Cited by 4,477
FaceForensics++: Learning to Detect Manipulated Facial Images
Rossler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., & Niessner, M. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00009 · Cited by 3,314 · cited 7×
“Google also a proposed Deepfake Detection dataset (DFD) [59] which contains 363 real videos and 3,000 deepfake videos, respectively.”
BackgroundMethodInfluentialVoxCeleb2: Deep Speaker Recognition
Chung, J. S., Nagrani, A., & Zisserman, A. (2018) · Interspeech 2018 · doi:10.21437/interspeech.2018-1929 · Cited by 2,256
MesoNet: a Compact Facial Video Forgery Detection Network
Afchar, D., Nozick, V., Yamagishi, J., & Echizen, I. (2018) · 2018 IEEE International Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs.2018.8630761 · Cited by 1,872
Celeb-DF: A Large-Scale Challenging Dataset for DeepFake Forensics
Li, Y., Yang, X., Sun, P., Qi, H., & Lyu, S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00327 · Cited by 1,846 · cited 4×
“There is a significant amount of research done in generating deepfake videos and a number of deepfake video datasets are proposed by many researchers [15, 24, 32, 34, 40, 91].”
BackgroundMethodInfluential
Research works printed but not linked: 8
- [2] Shruti Agarwal, Hany Farid, Yuming Gu, Mingming He, Koki Nagano, and Hao Li. 2019. Protecting World Leaders Against Deep Fakes. In CVPR Workshops . CVPRW, Berlin, 38-45. -
- [16] Nick Dufour and Andrew Gully. 2019. Contributing data to deepfake detection research. Google AI Blog (2019). -
- [17] Baruch Epstein, Ron Meir, and Tomer Michaeli. 2018. Joint autoencoders: a flexible meta-learning framework. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases . Springer, 494-509. -
- [20] Md Rashidul Hasan, Mustafa Jamil, MGRMS Rahman, et al. 2004. Speaker identification using mel frequency cepstral coefficients. variations 1, 4 (2004), 565-568. -
- [31] Nikita Kireev and Eugene Ilyushin. 2020. Review of existing text-to-speech algorithms. International Journal of Open Information Technologies 8, 7 (2020), 84-90. -
- [41] Iain McCowan, Jean Carletta, Wessel Kraaij, Simone Ashby, S Bourban, M Flynn, M Guillemot, Thomas Hain, J Kadlec, Vasilis Karaiskos, et al. 2005. The AMI meeting corpus. In Proceedings of the 5th international conference on methods and techniques in behavioral research , Vol. 88. Citeseer, 100. -
- [52] Henri J Nussbaumer. 1981. The fast Fourier transform. In Fast Fourier Transform and Convolution Algorithms . Springer, 80-111. -
- [69] M Sridevi, C Mala, and Siddhant Sanyam. 2012. Comparative study of image forgery and copy-move techniques. Advances in Computer Science, Engineering & Applications (2012), 715-723. -
Cited by
Items 101–151 of 151
MMDFD- A Multimodal Custom Dataset for Deepfake Detection
Asha, S., Vinod, P., & Menon, V. G. (2023) · International Conference on Contemporary Computing · doi:10.1145/3607947.3608013 · Cited by 3
A Novel Deepfake Detection Framework using Audio-Video-Textual FeaturesPreprint
Asha, S., Vinod, P., Amerini, I., & Menon, V. G. (2022) · Research Square · doi:10.21203/rs.3.rs-2390408/v1 · Cited by 3
WWW: Where, Which and Whatever Enhancing Interpretability in Multimodal Deepfake DetectionPreprint
Jung, J., Lee, S., Kang, J., & Na, Y. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2408.02954 · Cited by 3
Shiohara, K., Yamasaki, T., & Golyanik, V. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2601.02359 · Cited by 3
Sudharsana, P. P., Rajalaxmi, R. R., Gughan, R., Thamilselvan, R., Saranya, S., & Sruthi, K. (2024) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt61001.2024.10725767 · Cited by 2
Modal-Guided Multi-Domain Inconsistency Learning for Face Forgery Detection
Guo, Z., Zhang, B., Fan, J., Teng, Z., & Fan, J. (2024) · Applied Sciences · doi:10.3390/app15010229 · Cited by 2
A Hybrid Deep Learning Framework for Real and Deepfake Voice Detection
Murty, M., Tomar, S., & Koolagudi, S. G. (2026) · Circuits Systems and Signal Processing · doi:10.1007/s00034-025-03464-4 · Cited by 2
Zhu, G., Li, H.-S., Xia, H., & Song, S. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133067 · Cited by 2
Leave No Stone Unturned: Uncovering Holistic Audio-Visual Intrinsic Coherence for Deepfake Detection
Peng, J., Wang, Y., Li, Y., Kong, L., & Hong, X. (2026) · doi:10.1109/cvprf71909.2026.00639 · Cited by 2
WDC'22: 1st Workshop on the Security Implications of Deepfakes and Cheapfakes
Woo, S. S., Tariq, S., & Kim, H. (2022) · ACM Asia Conference on Computer and Communications Security (ASIA CCS) · doi:10.1145/3488932.3517204 · Cited by 2
Self-citationDevoX: Deep Voice Detection MLOps Framework for Crime Prevention in the Core-Edge Cloud
Seo, Y., Jo, H.-K., Roh, S., Sun, T.-J., Jeong, S.-W., Kim, H., Ngo, T.-T., & Huh, E. (2024) · International Conference on Information Networking · doi:10.1109/icoin59985.2024.10572202 · Cited by 2
Video_audio multimodal for deepfake detection
Sultan, D. A., & Ibrahim, L. M. (2024) · AIP conference proceedings · doi:10.1063/5.0236010 · Cited by 2
Detection of Quality Deep Fake Images and Videos Using Customised Convolutional Neural Networks
Mahar, A., Verma, P., & Singh, A. (2025) · International Conference on Advances in Computer Science, Electrical, Electronics, and Communication Technologies (CE2CT) · doi:10.1109/ce2ct64011.2025.10939891 · Cited by 3
America, U. S. O., & Polagani, S. S. (2025) · International Journal of Innovative Research in Science Engineering and Technology · doi:10.15680/ijirset.2025.1406001 · Cited by 1
FactorArmor: A Hierarchical Dual-Factor Framework with Attack Resilience for Face Forgery Detection
Liu, W., Fang, S., Hu, J., Xing, Q., & Wang, X. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228460 · Cited by 1
Hussain, R., Rahman, M. M., & Bhattacharjee, P. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-33805-1_8 · Cited by 1
He, Y., & Wang, S. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5740-0_36 · Cited by 1
Matli, W. (2026) · Universal Access in the Information Society · doi:10.1007/s10209-026-01338-3 · Cited by 1
Moufidi, A. (2024) · theses.fr (ABES) · doi:10.70675/9e5d03a4z911az4b73z9b34z33455082da04 · Cited by 1
Breast Cancer Radiogenomics Data Generation Using Combined Generative Adversarial Networks GANs
Anwar, S., Ali, S. A., Abdulla, D., Omekara, S. D., Mendiola, S., Wright, K., & Muhammed, S. A. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-46335-8_9
Duhan, K., & Kajal, A. (2025) · International Journal of Electrical and Electronics Engineering · doi:10.14445/23488379/ijeee-v12i3p104
Attention-Based Early and Late Fusion of Audio Visual for Deepfake Detection
Raj, S., Mathew, J., & Mondal, A. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-7175-5_20
DualStreamNet : Robust Audio-Video Deep Fake Media Detection Using Complimentary Information Fusion
Sheeranali, S., Ramachandra, R., & Venkatesh, S. K. (2025) · International Conference on Information Fusion (FUSION) · doi:10.23919/fusion65864.2025.11124073
Toward efficient multimodal fake news detection: issues, methods, and directions
Mikayelyan, A., Tadevosyan, A., & Kumar, S. (2025) · Machine learning for computational science and engineering · doi:10.1007/s44379-025-00033-z
Temporal Telepresence: Immersive Interfaces for TeleAbsence
Pillis, D. (2024) · DSpace@MIT (Massachusetts Institute of Technology)
Through the Lens: Benchmarking Deepfake Detectors Against Moiré-Induced DistortionsPreprint
Tariq, R., Heo, M., Woo, S. S., & Tariq, S. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.23225
Self-citationA Review on Deepfake Audio Recognition Using Generative AI
Dubey, D., Gupta, M., & Mattoo, A. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-8343-7_43
Aurora: Adaptive Audio-Video Multi-Scale Attention Fusion for Deepfake Detection
Xu, J., Chang, S., & Zhu, H. (2025) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads67057.2025.11322961
AI/ML Based Solution for Detection of Face and Voice Based Deep Fake Videos
Anand, R., Rakesh, T. K., Ram, S. S., & Varshan, M. S. S. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-15401-9_26 · Cited by 1
Deep-Fakes Detection in Media Forensics Using Deep Learning and Fusion Methods
Deshmukh, Y., Haque, M. J., & Bhaladhare, P. (2025) · International Conference for Advancement in Technology (ICONAT) · doi:10.1109/iconat66879.2025.11362482
Feature-Optimized Deepfake Audio Detection Using Machine Learning
Yarram, S. S. R., Balamurali, H. B., Reddy, M. M. S., Kumar, P. S. V., & Lal, G. J. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-14531-4_49
Use of machine learning for predicting stress episodes based on wearable sensor data
Pataca, A. O. (2025) · Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)
Amorós, B., & González, D. J. G. (2026) · Revista de Estilos de Aprendizaje · doi:10.55777/rea.v19i37.8603
Banik, S. (2026) · Preprints.org · doi:10.20944/preprints202604.1188.v1
Are DeepFakes Realistic Enough? Exploring Semantic Mismatch as a Novel Challenge
Deshmukh, S. N., Hambarde, K., Costa, J. C., Proença, H. P. M. C., & Roxo, T. (2026) · IEEE Access · doi:10.1109/access.2026.3730281
Panwar, P., Sonia, & Damini (2026) · International Conference on Computing for Sustainable Global Development · doi:10.23919/indiacom70271.2026.11526350
Deepfakes: relevancia penal para los bienes jurídicos personales
Salgado, N. M. (2026) · Communities in ADDI (University of the Basque Country)
Verma, B. K., Giri, S., & Saxena, A. (2026) · International Conference on Innovations in Computational Intelligence (ICICI) · doi:10.1109/icici68867.2026.11564891
Deepfake detection: A review of audio, visual and multimodal techniques
Kanwal, R., Ashraf, H., Jhanjhi, N. Z., & Mirza, Q. U. A. Z. Z. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.115845
HIL-MDF: A Human-in-the-Loop Multimodal Deepfake Detection System
El-Beheiry, H., Asmah, A., Zaher, O., Abdulwagid, M., & Moussa, S. M. (2026) · IEEE International Conference on Smart Sustainable Systems for Computer and Engineering Applications (3SCEA) · doi:10.1109/3scea68071.2026.11603194
Imbalance-Aware Cross-Modal Focal Modulation for Cross-Dataset Audio-Visual Deepfake Detection
Dokiey, S. M. B., Khan, T. M., & Qazi, E. U. H. (2026) · Future Internet · doi:10.3390/fi18070379
Khan, A., Aziz, M. A., Asif, M. J., Akhter, N., & Ahmad, R. F. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.20579
Devi, B. T., & Rajasekaran, R. (2026) · Research Square · doi:10.21203/rs.3.rs-10361285/v1
CiL-MVT: Multimodal Video Transformer for Robust Deepfake AuthenticationPreprint
Tanjung, M. A. P., Khair, R., & Haris, M. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7353768
AV-DeepFake-Net: Attention-Guided and Uncertainty-Aware Network for Audiovisual DeepFake Detection
Saleem, N., Hussain, A., Bourouis, S., Dhahbi, S., Dhahbi, A., Ali, A., & Zeng, Z. (2026) · International Journal of Interactive Multimedia and Artificial Intelligence · doi:10.9781/0m4b5v36
A REVIEW OF MULTIMODAL DEEPFAKE FORGERY DETECTION IN AUDIOVIDEO-TEXT
Ali, H., Ghous, H., Asim, M., Rashid, T., & Akhtar, H. M. U. (2026) · Journal of Applied Linguistics and TESOL (JALT)
Hybrid Machine Learning Models for Deepfake Detection in Multimedia Content
Jalbani, T. H., Qazi, S., Malookhani, J., & Shah, S. M. H. (2025) · Annual Methodological Archive Research Review
Shiohara, K., Yamasaki, T., & Golyanik, V. (2026) · doi:10.1109/cvprf71909.2026.00355
Ariyawong, P., Techatantiwong, J., & Aueawatthanaphisut, A. (2026) · International Conference on Advanced Machine Learning and Data Science (AMLDS) · doi:10.1109/amlds69611.2026.11724056
Zong, J., Lin, C., Liu, M., Xu, Z., Wang, J., Zhang, S., Jiang, P., Wang, L., & Dang, J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.30872
MDD-CR: End-to-end multimodal deepfake detection fusing spatio-temporal and spectrographic features
Das, A. K., & Naskar, R. (2026) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2026.105021
Metadata
- Authors
- Khalid, H., Kim, M., Tariq, S., & Woo, S. S.
- Affiliations
- Sungkyunkwan University (KR)
- Venue
- Proceedings of the 1st Workshop on Synthetic Multimedia - Audiovisual Deepfake Generation and Detection
- Publisher
- ACM
- Published
- 2021-10-20
- Pages
- 7-15
- OpenAlex
- W3197123936
- Cited by
- 110
- References
- 56
- Citations by year
- 2026: 16 · 2025: 34 · 2024: 27 · 2023: 19 · 2022: 13 · 2021: 1
- FWCI
- 4.90
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Research Foundation of Korea (NRF) grant funded by Korea government MSIT Basic Science Research Program (2020R1C1C1006004)
- IITP grant funded by the Korea government (MSIT) AI Graduate School Support Program (2019-0-00421)
- MSIT (Ministry of Science ICT) Korea under the High-Potential Individuals Global Training Program (2020-0-01550)
- IITP grant funded by the Korea government MSITOriginal Technology Development of Artificial Intelligence Industry (2021-0-00017)
- IITP grant funded by the Korea government (MSIT) Regional strategic industry convergence security core talent training business (2019-0-01343)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
- Physical Sciences › Computer Science › Signal Processing › Biometric Identification and Security
- Keywords
- deepfake detection, synthetic audio, voice cloning, face swapping
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.