Evaluation of an Audio-Video Multimodal Deepfake Dataset using Unimodal and Multimodal Detectors
Open accessThe DOI matches its Crossref record; 83 of the 83 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
VoxCeleb2: 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: 16
- Agarwal Shruti, 2019, Protecting World Leaders Against Deep Fakes. In CVPR Workshops. CVPRW
- 10.5555/3327546.3327667 · doi:10.5555/3327546.3327667
- Dufour Nick, 2019, Contributing data to deepfake detection research. Google AI Blog
- Epstein Baruch, 2018, Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, 494--509
- 10.5555/2969033.2969125 · doi:10.5555/2969033.2969125
- Hasan Md Rashidul, 2004, et almbox
- 10.5555/3327345.3327360 · doi:10.5555/3327345.3327360
- Khalid Hasam, 2021, Woo
- Kireev Nikita, 2020, Review of existing text-to-speech algorithms, International Journal of Open Information Technologies, 8, 84
- McCowan Iain, 2005, The AMI meeting corpus. In Proceedings of the 5th international conference on methods and techniques in behavioral research, 88
- Nussbaumer Henri J, Fast Fourier Transform and Convolution Algorithms
- Proceedings of the IEEE/CVF International Conference on Computer Vision. 1--11
- Sabir Ekraam, 2019, Interfaces (GUI), 3
- Sridevi M, 2012, Engineering & Applications
- Tan Mingxing, 2019, International Conference on Machine Learning. PMLR, 6105--6114
- Wang Yuxuan, 2017, et almbox
Cited by
A Review of Modern Audio Deepfake Detection Methods: Challenges and Future Directions
Almutairi, Z., & Elgibreen, H. (2022) · Algorithms · doi:10.3390/a15050155 · Cited by 187
“They used an image-based approach, which required a special transformation of the data, and the authors found that the model proposed failed to correctly classify new audio signals indicating that the model is not general enough.”
Ilyas, H., Javed, A., & Malik, K. M. (2023) · Applied Soft Computing · doi:10.1016/j.asoc.2023.110124 · Cited by 186
Deepfake Media Forensics: Status and Future Challenges
Amerini, I., Barni, M., Battiato, S., Bestagini, P., Boato, G., Bruni, V., Caldelli, R., De Natale, F., De Nicola, R., Guarnera, L., et al. (2025) · Journal of Imaging · doi:10.3390/jimaging11030073 · Cited by 113
Cai, Z., Stefanov, K., Dhall, A., & Hayat, M. (2022) · 2022 International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta56598.2022.10034605 · Cited by 99
“Similar to [65] the proposed dataset includes three variations of deepfake data,”
ResultA Robust Approach to Multimodal Deepfake Detection
Salvi, D., Liu, H., Mandelli, S., Bestagini, P., Zhou, W., Zhang, W., & Tubaro, S. (2023) · Journal of Imaging · doi:10.3390/jimaging9060122 · Cited by 96
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
- 83
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Evaluation of an Audio-Video Multimodal Deepfake Dataset using Unimodal and Multimodal Detectors. https://app.cochat.ai/papers/10.1145/3476099.3484315
- The paper
- Khalid, H., Kim, M., Tariq, S., & Woo, S. S. (2021). Evaluation of an Audio-Video Multimodal Deepfake Dataset using Unimodal and Multimodal Detectors. Proceedings of the 1st Workshop on Synthetic Multimedia - Audiovisual Deepfake Generation and Detection. https://doi.org/10.1145/3476099.3484315
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.