The Creation and Detection of Deepfakes: A Survey
Open accessThe DOI matches its Crossref record; 164 of the 165 references it cites were found in a registry or an index.
Abstract
Generative deep learning algorithms have progressed to a point where it is difficult to tell the difference between what is real and what is fake. In 2018, it was discovered how easy it is to use this technology for unethical and malicious applications, such as the spread of misinformation, impersonation of political leaders, and the defamation of innocent individuals. Since then, these “deepfakes” have advanced significantly. In this article, we explore the creation and detection of deepfakes and provide an in-depth view as to how these architectures work. The purpose of this survey is to provide the reader with a deeper understanding of (1) how deepfakes are created and detected, (2) the current trends and advancements in this domain, (3) the shortcomings of the current defense solutions, and (4) the areas that require further research and attention.
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 cited source doesn’t support the claim as written.
In the citing paper
“The survey lacks discussion on the technical challenges associated with generation and detection systems.”
From Deepfake video detection: challenges and opportunities (2024) · cites this paper as Mirsky and Lee 2021
Checked by a reasoning model — may be wrong.
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
“Furthermore, it has been proven that deep neural networks tend to achieve better performance than traditional image forensic tools [9].”
From DFDT: An End-to-End DeepFake Detection Framework Using Vision Transformer (2022) · cites this paper as [9]
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
“Faceswapping can also be difficult to identify it as a deepfake when the pictures artifacts are hidden behind the compression artifacts (Mirsky and Lee, 2021).”
From Audio deepfakes: A survey (2023) · cites this paper as Mirsky and Lee, 2021
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
“While there are several surveys of passive DF detection that examine specific modalities in isolation [5-9], the field requires a holistic analysis that transcends these single approaches.”
From Deepfake detection across image, video, and audio: a comprehensive survey with empirical evaluation of generalization and robustness (2026) · cites this paper as [6]
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
“Current survey papers [5-9, 15, 15, 16] primarily focus on reviewing detection methods based on their accuracy performance within the same dataset (within-domain evaluation), which achieves high accuracy (often exceeding 95%).”
From Deepfake detection across image, video, and audio: a comprehensive survey with empirical evaluation of generalization and robustness (2026) · cites this paper as [6]
Experimental — accuracy not yet measured
8 more claims about this paper
Create a free account to see every claim other papers make about this one.
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
Image-to-Image Translation with Conditional Adversarial Networks
Isola, P., Zhu, J.-Y., Zhou, T., & Efros, A. A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.632 · Cited by 22,930 · cited 1×
“One popular version is the pix2pix framework which enables translations from one image domain to another [12].”
BackgroundPerceptual Losses for Real-Time Style Transfer and Super-Resolution
Johnson, J., Alahi, A., & Fei-Fei, L. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46475-6_43 · Cited by 11,283
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Finn, C., Abbeel, P., & Levine, S. (2017) · arXiv · doi:10.48550/arxiv.1703.03400 · Cited by 8,512 · cited 1×
“4) Few-Shot Learning: In [85], the authors demonstrate the few-shot learning technique of [86] on a pix2pixHD network and the network of [82].”
BackgroundAccurate Image Super-Resolution Using Very Deep Convolutional Networks
Kim, J., Lee, J. K., & Lee, K. M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.182 · Cited by 7,870 · cited 1×
“s [111] can be evaded by reenacting the entire head and by learning the mannerisms from the same databases. Models which identify blurred content [115] are affected by noise and sharpening GANs [42], [151], and models which search for the boundary where the face was blended in [112]–[117] do not work on deepfakes pass…”
BackgroundImproved Techniques for Training GANs
Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., & Chen, X. (2016) · arXiv · doi:10.48550/arxiv.1606.03498 · Cited by 6,965 · cited 1×
“) Similar to Lperc , there is a feature matching loss (LFM ) [133] which uses the last output of a network.”
BackgroundAnalyzing and Improving the Image Quality of StyleGAN
Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., & Aila, T. (2019) · arXiv · doi:10.48550/arxiv.1912.04958 · Cited by 6,332 · cited 1×
“Human face and body synthesis techniques such as [78] (used in Fig.”
MethodAnalyzing and Improving the Image Quality of StyleGAN
Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., & Aila, T. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00813 · Cited by 6,332
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
Wang, T.-C., Liu, M.-Y., Zhu, J.-Y., Tao, A., Kautz, J., & Catanzaro, B. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00917 · Cited by 5,360
A morphable model for the synthesis of 3D faces
Blanz, V., & Vetter, T. (1999) · Proceedings of the 26th annual conference on Computer graphics and interactive techniques - SIGGRAPH '99 · doi:10.1145/311535.311556 · Cited by 4,710
StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation
Choi, Y., Choi, M., Kim, M., Ha, J.-W., Kim, S., & Choo, J. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00916 · Cited by 4,163
Research works printed but not linked: 32
- 2020, Retrieved
- [2] Kfir Aberman, Mingyi Shi, Jing Liao, D Liscbinski, Baoquan Chen, and Daniel Cohen-Or. 2019. Deep Video-Based Performance Cloning. In Computer Graphics Forum . Wiley Online Library. -
- [6] Shruti Agarwal, Hany Farid, Yuming Gu, Mingming He, Koki Nagano, and Hao Li. 2019. Protecting World Leaders Against Deep Fakes. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops . 38-45. -
- [12] Arije Antinori. 2019. Terrorism and DeepFake: from Hybrid Warfare to Post-Truth Warfare in a Hybrid World. In ECIAIR 2019 European Conference on the Impact of Artificial Intelligence and Robotics . Academic Conferences and publishing limited, 23. -
- [13] Hadar Averbuch-Elor, Daniel Cohen-Or, Johannes Kopf, and Michael F. Cohen. 2017. Bringing Portraits to Life. ACMTransactions on Graphics (Proceeding of SIGGRAPH Asia 2017) 36, 6 (2017), 196. -
- [19] Volker Blanz, Curzio Basso, Tomaso Poggio, and Thomas Vetter. 2003. Reanimating faces in images and video. In Computer graphics forum , Vol. 22. Wiley Online Library, 641-650. -
- [20] Volker Blanz, Kristina Scherbaum, Thomas Vetter, and Hans-Peter Seidel. 2004. Exchanging faces in images. In Computer Graphics Forum , Vol. 23. Wiley Online Library, 669-676. -
- [44] Chi-Ying Chen et al. 2019. A Trusting News Ecosystem Against Fake News from Humanity and Technology Perspectives. In 2019 19th International Conference on Computational Science and Its Applications (ICCSA) . IEEE, 132-137. -
- [46] Liqian Ma et al. 2018. Disentangled person image generation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . 99-108. -
- [47] Pavel Korshunov et al. 2019. Tampered Speaker Inconsistency Detection with Phonetically Aware Audio-visual Features. In International Conference on Machine Learning . -
- [48] Shengju Qian et al. 2019. Make a Face: Towards Arbitrary High Fidelity Face Manipulation. In Proceedings of the IEEE International Conference on Computer Vision . -
- [61] Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. In Advances in neural information processing systems . 2672-2680. -
- [62] Kuangxiao Gu, Yuqian Zhou, and Thomas S Huang. 2020. FLNet: Landmark Driven Fetching and Learning Network for Faithful -
- [63] David Guera and Edward J Delp. 2018. Deepfake video detection using recurrent neural networks. In IEEE Conference on Advanced Video and Signal Based Surveillance (AVSS) . IEEE, 1-6. 30. Talking Facial Animation Synthesis.. In AAAI . 10861-10868. -
- [66] Holly Kathleen Hall. 2018. Deepfake Videos: When Seeing Isn't Believing. Cath. UJL & Tech 27 (2018), 51. -
- 2019, Retrieved
- [74] Amir Jamaludin, Joon Son Chung, and Andrew Zisserman. 2019. You said that?: Synthesising talking faces from audio. International Journal of Computer Vision (2019), 1-13. -
- [81] Hasam Khalid and Simon S Woo. 2020. OC-FakeDect: Classifying Deepfakes Using One-Class Variational Autoencoder. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops . 656-657. -
- [85] Marissa Koopman, Andrea Macarulla Rodriguez, and Zeno Geradts. 2018. Detection of Deepfake Video Manipulation. In Conference: IMVIP . -
- [109] Yisroel Mirsky, Tom Mahler, Ilan Shelef, and Yuval Elovici. 2019. CT-GAN: Malicious Tampering of 3D Medical Imagery using Deep Learning. In USENIX Security Symposium 2019 . -
- [112] Joel Ruben Antony Moniz, Christopher Beckham, Simon Rajotte, Sina Honari, and Chris Pal. 2018. Unsupervised depth estimation, 3d face rotation and replacement. In Advances in Neural Information Processing Systems . 9736-9746. -
- [114] Ryota Natsume, Tatsuya Yatagawa, and Shigeo Morishima. 2018. FSNet: An Identity-Aware Generative Model for Image-Based Face Swapping. In Asian Conference on Computer Vision . Springer, 117-132. -
- [128] Albert Pumarola, Antonio Agudo, Aleix M Martinez, Alberto Sanfeliu, and Francesc Moreno-Noguer. 2019. GANimation: One-shot anatomically consistent facial animation. International Journal of Computer Vision (2019), 1-16. -
- [129] Md Shohel Rana and Andrew H Sung. 2020. DeepfakeStack: A Deep Ensemble-based Learning Technique for Deepfake Detection. In 2020 7th IEEE International Conference on Cyber Security and Cloud Computing (CSCloud)/2020 6th IEEE International Conference on Edge Computing and Scalable Cloud (EdgeCom) . IEEE, 70-75. -
- [138] Shawn Shan, Emily Wenger, Jiayun Zhang, Huiying Li, Haitao Zheng, and Ben Y Zhao. 2020. Fawkes: Protecting Privacy against Unauthorized Deep Learning Models. In 29th f USENIX g Security Symposium ( f USENIX g Security 20) . 1589-1604. -
- 2018, Retrieved
- [148] Jose Sotelo, Soroush Mehri, Kundan Kumar, Joao Felipe Santos, Kyle Kastner, Aaron Courville, and Yoshua Bengio. 2017. Char2wav: End-to-end speech synthesis. Openreview.net (2017). -
- [153] Shahroz Tariq, Sangyup Lee, Hoyoung Kim, Youjin Shin, and Simon S Woo. 2018. Detecting both machine and human created fake face images in the wild. In Proceedings of the 2nd International Workshop on Multimedia Privacy and Security . ACM, 81-87. -
- [164] Konstantinos Vougioukas, Stavros Petridis, and Maja Pantic. 2019. End-to-End Speech-Driven Realistic Facial Animation with Temporal GANs. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops . 37-40. -
- [168] Ting-Chun Wang, Ming-Yu Liu, Andrew Tao, Guilin Liu, Jan Kautz, and Bryan Catanzaro. 2019. Few-shot Video-to-Video Synthesis. In Advances in Neural Information Processing Systems (NeurIPS) . -
- [187] Ying Zhang, Lilei Zheng, and Vrizlynn LL Thing. 2017. Automated face swapping and its detection. In 2017 IEEE 2nd International Conference on Signal and Image Processing (ICSIP) . IEEE, 15-19. -
- [192] Jun-Yan Zhu, Taesung Park, Phillip Isola, and Alexei A Efros. 2017. Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the IEEE international conference on computer vision . 2223-2232. -
Cited by
Feuerriegel, S., Hartmann, J., Janiesch, C., & Zschech, P. (2024) · Business & Information Systems Engineering · doi:10.1007/s12599-023-00834-7 · Cited by 2,267
“Notwithstanding, AI-generated disinformation has previously evolved as so-called deepfakes (Mirsky and Lee 2021), but recent advances in generative AI reduce the cost of creating such disinformation and allow for unprecedented personalization.”
Generative artificial intelligence
Banh, L., & Strobel, G. (2023) · Electronic Markets · doi:10.1007/s12525-023-00680-1 · Cited by 579
“…GAI models provides starting points for new applications and business models for misuse and criminals, ultimately being leveraged to spread misinformation and influence the media and politics, or to defraud individuals and businesses (Hart-mann et al., 2023; Kreps et al., 2022; Mirsky & Lee, 2022).”
BackgroundChallenges in deploying machine learning: A survey of case studies
Paleyes, A., Urma, R.-G., & Lawrence, N. D. (2023) · ACM Computing Surveys · doi:10.1145/3533378 · Cited by 638
“Closely related to this question is the growing concern of fake content being generated with ML, such as deepfake images and video, which can be easily used for the wrong purposes [95].”
BackgroundDeepfake 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
Metadata
- Authors
- Mirsky, Y., & Lee, W.
- Affiliations
- Georgia Institute of Technology (US)
- Venue
- ACM Computing Surveys
- Published
- 2021-01-02
- Volume
- 54
- Issue
- 1
- Pages
- 1-41
- ISSN
- 0360-0300 (ISSN-L)
- 1557-7341
- OpenAlex
- W3019200173
- Semantic Scholar
- 97ac037b7589d9d0f2cb5109aa2b095ad06067fd
- Cited by
- 863
- References
- 81
- Citations by year
- 2026: 202 · 2025: 213 · 2024: 163 · 2023: 131 · 2022: 90 · 2021: 53
- FWCI
- 39.29
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- ACM Computing Surveys (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- 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
- deepfakes, deepfake detection, deepfake generation, generative adversarial networks, misinformation, impersonation, defamation, synthetic media
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.