WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection
The DOI matches its Crossref record; 25 of the 26 references it cites were found in a registry or an index.
Abstract
In recent years, the abuse of a face swap technique called deepfake has raised enormous public concerns. So far, a large number of deepfake videos (known as "deepfakes") have been crafted and uploaded to the internet, calling for effective countermeasures. One promising countermeasure against deepfakes is deepfake detection. Several deepfake datasets have been released to support the training and testing of deepfake detectors, such as DeepfakeDetection [1] and FaceForensics++ [23]. While this has greatly advanced deepfake detection, most of the real videos in these datasets are filmed with a few volunteer actors in limited scenes, and the fake videos are crafted by researchers using a few popular deepfake softwares. Detectors developed on these datasets may become less effective against real-world deepfakes on the internet. To better support detection against real-world deepfakes, in this paper, we introduce a new dataset WildDeepfake, which consists of 7,314 face sequences extracted from 707 deepfake videos collected completely from the internet. WildDeepfake is a small dataset that can be used, in addition to existing datasets, to develop and test the effectiveness of deepfake detectors against real-world deepfakes. We conduct a systematic evaluation of a set of baseline detection networks on both existing and our WildDeepfake datasets, and show that WildDeepfake is indeed a more challenging dataset, where the detection performance can decrease drastically. We also propose two (eg. 2D and 3D) Attention-based Deepfake Detection Networks (ADDNets) to leverage the attention masks on real/fake faces for improved detection. We empirically verify the effectiveness of ADDNets on both existing datasets and WildDeepfake. The dataset is available at: https://github.com/deepfakeinthewild/deepfake-in-the-wild.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“Particularly, in the frame-level setting the DFDT model has achieved 99.41%, 99.31%, and 81.35% on an accuracy score corresponding to FaceForensics++ (raw) [49], Celeb-DF (V2) [55], and WildDeepfake [56], respectively.”
From DFDT: An End-to-End DeepFake Detection Framework Using Vision Transformer (2022) · cites this paper as [56]
In the citing paper
“WildDeepfake collected deepfake videos from the internet, highlighting that detectors trained on controlled datasets may fail under real-world distributions and that performance can drop drastically [39].”
From A Review of Tools and Technologies to Combat Deepfakes (2026) · cites this paper as [39]
In the citing paper
“In-the-wild datasets and public evaluation programs reinforce that realistic deployment conditions can differ substantially from research datasets”
From A Review of Tools and Technologies to Combat Deepfakes (2026) · cites this paper as [39]
In the citing paper
“First, content-based deepfake detectors can achieve strong in-domain performance, but their reliability drops under cross-dataset shift, unseen generators, compression, and adversarial post-processing.”
From A Review of Tools and Technologies to Combat Deepfakes (2026) · cites this paper as [39]
In the citing paper
“Foundational benchmarks have been instrumental in advancing the accuracy of deepfake detectors.”
From From Black Boxes to Glass Boxes: Explainable AI for Trustworthy Deepfake Forensics (2025) · cites this paper as [50]
1 more claim about this paper
Create a free account to see every claim other papers make about this one.
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
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
(2008) · Journal of Machine Learning Research · Cited by 33,051
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
MobileNetV2: Inverted Residuals and Linear Bottlenecks
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00474 · Cited by 28,755 · cited 1×
“We then extract features for the face regions using an ImageNet-pretrained MobileNetV2 [25] network.”
MethodGAN(Generative Adversarial Nets)
(2017) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.29.5_177_2 · Cited by 19,270
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
Carreira, J., & Zisserman, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.502 · Cited by 9,570
Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks
Zhang, K., Zhang, Z., Li, Z., & Qiao, Y. (2016) · IEEE Signal Processing Letters · doi:10.1109/lsp.2016.2603342 · Cited by 6,214 · cited 1×
“We use the Mtcnn [32] face detector to identify the face regions in each video frame.”
MethodFaceForensics++: 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 4×
“The FaceFornesics++ [23] dataset has 1,000 real videos collected from YouTube, based on which 1,000 deepfake videos were generated by applying each of the 4 face modification techniques: Deepfake [2], Face2Face [29], Faceswap [4] and Neural Texture [28] (eg. overall 4,000 face modification videos…”
MethodInfluentialDlib-ml: A Machine Learning Toolkit
King, D. E. (2009) · doi:10.5555/1577069.1755843 · Cited by 2,777 · cited 1×
“Next, we use the facial landmark extracted by dlib[13] landmark detector to align all the faces in a face sequence.”
MethodLearning Spatio-Temporal Representation with Pseudo-3D Residual Networks
Qiu, Z., Yao, T., & Mei, T. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.590 · Cited by 1,874 · cited 1×
“For sequence-level detection, we compare our ADDNet-3D with P3D [22], C3D [30] and I3D [6], which are three state-of-the-art 3D networks for video recognition.”
MethodMesoNet: 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 2×
“This drives the collection of several deepfake datasets such as Celeb-DF [20], UADFV [31], Deepfake-TIMIT [15] and FaceForensics++ [23].”
MethodFace2Face: Real-Time Face Capture and Reenactment of RGB Videos
Thies, J., Zollhofer, M., Stamminger, M., Theobalt, C., & Niessner, M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.262 · Cited by 1,747
Deferred neural rendering: image synthesis using neural textures
Thies, J., Zollhöfer, M., & Nießner, M. (2019) · ACM Transactions on Graphics · doi:10.1145/3306346.3323035 · Cited by 1,356 · cited 1×
“…[23] dataset has 1,000 real videos collected from YouTube, based on which 1,000 deepfake videos were generated by applying each of the 4 face modification techniques: Deepfake [2], Face2Face [29], Faceswap [4] and Neural Texture [28] (eg. overall 4,000 face modification videos were created).”
MethodDeepfake Video Detection Using Recurrent Neural Networks
Guera, D., & Delp, E. J. (2018) · 2018 15th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2018.8639163 · Cited by 1,285 · cited 2×
“Güera et al. [11] revealed that the frame sequence of deepfake videos have unique characteristics, which differentiates them from unmodified videos.”
BackgroundMethodFace X-Ray for More General Face Forgery Detection
Li, L., Bao, J., Zhang, T., Yang, H., Chen, D., Wen, F., & Guo, B. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00505 · Cited by 1,211
Exposing Deep Fakes Using Inconsistent Head Poses
Yang, X., Li, Y., & Lyu, S. (2019) · ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2019.8683164 · Cited by 1,196
In Ictu Oculi: Exposing AI Created Fake Videos by Detecting Eye Blinking
Li, Y., Chang, M.-C., & Lyu, S. (2018) · 2018 IEEE International Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs.2018.8630787 · Cited by 1,089
Self-citationExposing DeepFake Videos By Detecting Face Warping Artifacts
Li, Y., & Lyu, S. (2018) · arXiv · doi:10.48550/arxiv.1811.00656 · Cited by 785 · cited 1×
“Li et al. introduced two different meth-ods [18, 19] to identify possible "artifacts" or eye blinking defects in deepfake videos.”
BackgroundFakeCatcher: Detection of Synthetic Portrait Videos using Biological Signals
Ciftci, U. A., Demir, I., & Yin, L. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3009287 · Cited by 499
DeepFakes: a New Threat to Face Recognition? Assessment and Detection
Korshunov, P., & Marcel, S. (2018) · arXiv · doi:10.48550/arxiv.1812.08685 · Cited by 497 · cited 9×
“Particularly, I3D achieves a high detection accuracy of > 89% on the four DF-TIMIT and FF++ datasets, while C3D has an accuracy of 73.18% on DFD.”
MethodInfluentialThe Deepfake Detection Challenge (DFDC) Preview Dataset
Dolhansky, B., Howes, R., Pflaum, B., Baram, N., & Ferrer, C. C. (2019) · arXiv · doi:10.48550/arxiv.1910.08854 · Cited by 413 · cited 3×
“These fake videos have raised enormous public concerns for their huge risks to create political distress, blackmail someone or even fake terrorism events [9].”
BackgroundMethodInfluentialC3D: Generic Features for Video Analysis.
Tran, D., Bourdev, L. D., Fergus, R., Torresani, L., & Paluri, M. (2014) · Cited by 392
Sanderson, C. (2002) · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · Cited by 56
Research works printed but not linked: 5
- 2019. Deep Fake Detection Dataset. https://ai.googleblog.com/2019/09/ contributing-data-to-deepfake-detection.html Accessed October 29, 2019 . 2019. Deep Fake Detection Dataset. https://ai.googleblog.com/2019/09/ contributing-data-to-deepfake-detection.html Accessed October 29, 2019.
- F. Chollet . 2017 . Xception: Deep learning with depthwise separable convolutions. In CVPR. F. Chollet. 2017. Xception: Deep learning with depthwise separable convolutions. In CVPR.
- I. Goodfellow J. Pouget-Abadie M. Mirza B. Xu D. Warde-Farley S. Ozair A. Courville and Y. Bengio. 2014. Generative Adversarial Nets. In NIPS. I. Goodfellow J. Pouget-Abadie M. Mirza B. Xu D. Warde-Farley S. Ozair A. Courville and Y. Bengio. 2014. Generative Adversarial Nets. In NIPS.
- K. He , X. Zhang , S. Ren , and J. Sun. 201 6. Identity Mappings in Deep Residual Networks. In ECCV. K. He, X. Zhang, S. Ren, and J. Sun. 2016. Identity Mappings in Deep Residual Networks. In ECCV.
- D. Kingma and J. Ba. 201 4. Adam: A method for stochastic optimization. In arXiv:1412.6980. D. Kingma and J. Ba. 2014. Adam: A method for stochastic optimization. In arXiv:1412.6980. · arXiv
Cited by
Deepfake Detection: A Systematic Literature Review
Rana, M. S., Nobi, M. N., Murali, B., & Sung, A. H. (2022) · IEEE Access · doi:10.1109/access.2022.3154404 · Cited by 573
Masood, M., Nawaz, M., Malik, K. M., Javed, A., Irtaza, A., & Malik, H. (2023) · Applied Intelligence · doi:10.1007/s10489-022-03766-z · Cited by 543
End-to-End Reconstruction-Classification Learning for Face Forgery Detection
Cao, J., Ma, C., Yao, T., Chen, S., Ding, S., & Yang, X. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00408 · Cited by 428
“Cross-dataset evaluation in terms of AUC (%) and EER (%) by training on WildDeepfake [17].”
BackgroundMethodInfluentialLearning Self-Consistency for Deepfake Detection
Zhao, T., Xu, X., Xu, M., Ding, H., Xiong, Y., & Xia, W. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01475 · Cited by 383
“To support the research on detecting the other types of face manipulations, several deepfake datasets are released [57, 19, 41, 10, 28, 8, 15, 61] and countermeasures have been introduced.”
Deepfake detection using deep learning methods: A systematic and comprehensive review
Heidari, A., Jafari Navimipour, N., Dag, H., & Unal, M. (2024) · WIREs Data Mining and Knowledge Discovery · doi:10.1002/widm.1520 · Cited by 349
“Also, some approaches, such as the Hidden Markov Models (HMM) based speech synthesis system, are proposed to improve the range of voice characteristics or talking patterns (Zi et al., 2020).”
Method
Metadata
- Authors
- Zi, B., Chang, M., Chen, J., Ma, X., & Jiang, Y.-G.
- Affiliations
- Fudan University (CN)
- Deakin University (AU)
- Venue
- Proceedings of the 28th ACM International Conference on Multimedia
- Publisher
- ACM
- Published
- 2020-10-12
- Pages
- 2382-2390
- OpenAlex
- W3092879151
- Cited by
- 448
- References
- 26
- Citations by year
- 2026: 87 · 2025: 122 · 2024: 107 · 2023: 79 · 2022: 36 · 2021: 16 · 2020: 1
- FWCI
- 10.18
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM International Conference on Multimedia (ACM MM) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Keywords
- deepfake detection, deepfake datasets, face forensics
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.