The Creation and Detection of Deepfakes: A Survey
Open accessThe DOI matches its Crossref record; 162 of the 162 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: 49
- 2020, Retrieved
- Aberman Kfir, Computer Graphics Forum
- Agarwal Shruti, 2019, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 38--45
- Agarwal Sakshi, 2019, Varshney
- Antinori Arije, 2019, ECIAIR 2019 European Conference on the Impact of Artificial Intelligence and Robotics. Academic Conferences and Publishing Limited, 23
- Averbuch-Elor Hadar, 2017, Cohen
- Blanz Volker, Computer Graphics Forum
- Blanz Volker, Computer Graphics Forum
- Chan Caroline, Proceedings of the IEEE International Conference on Computer Vision. 5933--5942
- Chi-Ying, Forbes 2019 19th International Conference on Computational Science and Its Applications (ICCSA). IEEE, 132--137
- Liqian, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 99--108
- Pavel, International Conference on Machine Learning.
- Shengju, Proceedings of the IEEE International Conference on Computer Vision.
- 10.5555/3305381.3305498 · doi:10.5555/3305381.3305498
- Fraga-Lamas Paula, 2019, Fernandez-Carames
- 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. 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.
- Gu Kuangxiao, 2020, Huang
- Guera David, IEEE Conference on Advanced Video and Signal Based Surveillance (AVSS). IEEE, 1--6.
- Hall Holly Kathleen, 2018, Deepfake videos: When seeing isn’t believing. Cath. UJL 8 Tech 27
- Hao Karen, The biggest threat of deepfakes isn
- 2019, Retrieved
- Isola Phillip, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1125--1134
- Jamaludin Amir, 2019, Joon Son Chung, and Andrew Zisserman
- Jia Ye, 2018, Yonghui Wu, et al.
- Khalid Hasam, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. 656--657
- Koopman Marissa, 2018, Conference: IMVIP.
- Li Yuezun, 2019, Retrieved
- Li Yuezun, 2019, IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).
- Li Yuheng, 2019, Utkarsh Ojha, and Yong Jae Lee.
- Masi Iacopo, 2020, Shenoy Pratik Gurudatt
- Mirsky Yisroel, 2019, USENIX Security Symposium
- 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. 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.
- Natsume Ryota, 2018, Asian Conference on Computer Vision. Springer, 117--132
- Pumarola Albert, 2019, International Journal of Computer Vision
- 2020, Shohel Rana and Andrew H. Sung
- Schwartz Oscar, 2020, You thought fake news was bad? The Guardian. Retrieved
- Shan Shawn, Proceedings of the 29th {USENIX} Security Symposium ({USENIX} Security 20)
- 2018, Retrieved
- Siarohin Aliaksandr, Advances in Neural Information Processing Systems 32. Curran Associates
- Sotelo Jose, 2017, Kyle Kastner, Aaron Courville, and Yoshua Bengio.
- Tariq Shahroz, Proceedings of the 2nd International Workshop on Multimedia Privacy and Security. ACM, 81--87
- Vougioukas Konstantinos, 2019, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 37--40
- Wang Sheng-Yu, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 7
- 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). 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).
- Zellers Rowan, Advances in Neural Information Processing Systems 32. Curran Associates
- Zhang Yunxuan, 2019, Chen Change Loy, and Ziwei Liu
- Zhang Ying, Proceedings of the 2017 IEEE 2nd International Conference on Signal and Image Processing (ICSIP). IEEE, 15--19
- Zhou Yipin, 2019, Berg
- Zhu Jun-Yan, Proceedings of the IEEE International Conference on Computer Vision. 2223--2232
Cited by
Items 301–400 of 982
Impact of face swapping and data augmentation on sign language recognition
Perea-Trigo, M., López-Ortiz, E. J., Morillo, L. M. S., Álvarez-García, J. A., & Vegas-Olmos, J. J. (2024) · Universal Access in the Information Society · doi:10.1007/s10209-024-01133-y · Cited by 11
“Mirsky et al. [47] categorize the media content generated by deepfakes into four types: reenactment [48], where the source is used to drive the expression, mouth, gaze, pose, or body of the desired target; replacement [49], among which is face swapping, replacing the target’s content with that of…”
Daume, S., Bjersér, P., & Galaz, V. (2023) · Current Opinion in Environmental Sustainability · doi:10.1016/j.cosust.2023.101384 · Cited by 10
Robust cross-dataset deepfake detection with multitask self-supervised learning
Batagelj, B., Kronovšek, A., Štruc, V., & Peer, P. (2025) · ICT Express · doi:10.1016/j.icte.2025.02.011 · Cited by 15
Deepfakes and Victimology: Exploring the Impact of Digital Manipulation on Victims
Ali, M., Fernando, Z. J., Huda, C., & Mahmutarom, M. (2025) · Substantive Justice International Journal of Law · doi:10.56087/substantivejustice.v8i1.306 · Cited by 22
HSFF-Net: Hierarchical spectral-feature fusion network for deepfake detection and localization
Han, R., Wang, X., Bai, N., Hou, J., Zhang, W., & Li, J. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.107967 · Cited by 14
Multi-level feature fusion for generalized face forgery detection
Ghosh, T., & Naskar, R. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.131235 · Cited by 12
Tsalakanidou, F., Papadopoulos, S., Mezaris, V., Kompatsiaris, I. Y., Gray, B., Tsabouraki, D., Kalogerini, M., Negro, F., Montagnuolo, M., de Vos, J., et al. (2021) · IFIP advances in information and communication technology · doi:10.1007/978-3-030-79150-6_7 · Cited by 12
The MeVer DeepFake Detection Service: Lessons Learnt from Developing and Deploying in the Wild
Baxevanakis, S., Kordopatis-Zilos, G., Galopoulos, P., Apostolidis, L., Levacher, K., Schlicht, I. B., Teyssou, D., Kompatsiaris, I. Y., & Papadopoulos, S. (2022) · doi:10.1145/3512732.3533587 · Cited by 12
“Numerous surveys and literature reviews have been published following the recent explosion in DeepFake research [38, 45, 49, 55].”
BackgroundEvaluating Trustworthiness and Racial Bias in Face Recognition APIs Using Deepfakes
Tariq, S., Jeon, S., & Woo, S. S. (2023) · Computer · doi:10.1109/mc.2023.3234978 · Cited by 16
“Mirsky and Lee 37 broadly classify deep-fakes into three categories: replacement, reenactment, and synthesis.”
BackgroundRobust DeepFake Detection Method based on Ensemble of ViT and CNN
Ha, H. N., Kim, M., Han, S., & Lee, S. (2023) · ACM Symposium on Applied Computing · doi:10.1145/3555776.3577769 · Cited by 17
“Various studies have been conducted on DeepFake detection based on a large scale dataset made available through this competition, and most of these studies perform inspection with a method to find artifacts generated in DeepFake through a convolutional neural network(CNN), which has the best performance in general in…”
MethodExploring Neurophysiological Responses to Cross-Cultural Deepfake Videos
Khan, M. R., Naeem, S., Tariq, U., Dhall, A., Khan, M. N. A., Al Shargie, F., & Al-Nashash, H. (2023) · International Cconference on Multimodal Interaction · doi:10.1145/3610661.3617148 · Cited by 10
Conclusion: Misinformation and AI—How Algorithms Generate and Manipulate Misinformation
Shin, D. (2024) · Springer eBooks · doi:10.1007/978-3-031-52569-8_10 · Cited by 11
Online Fake News Opinion Spread and Belief Change: A Systematic Review
Altoe, F., Moreira, C., Pinto, H. S., & Jorge, J. A. (2024) · Human Behavior and Emerging Technologies · doi:10.1155/2024/1069670 · Cited by 17
Can You Tell Real from Fake Face Images? Perception of Computer-Generated Faces by Humans
Bozkir, E., Riedmiller, C., Skodras, A. N., Kasneci, G., & Kasneci, E. (2024) · ACM Transactions on Applied Perception · doi:10.1145/3696667 · Cited by 17
“For this reason, researchers also looked into how to identify AI-generated media and deepfakes in an automated way [40, 53, 66, 69, 70, 85] and found that deep learning methods outperform the others in the forgery detection task in videos with an additional improvement when domain-specific…”
Steganography beyond space-time with chain of multimodal AI
Chang, C., & Echizen, I. (2025) · Scientific Reports · doi:10.1038/s41598-025-97238-2 · Cited by 13
Robust Face-Swap Detection Based on 3D Facial Shape Information
Guan, W., Wang, W., Dong, J., Peng, B., & Tan, T. N. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20497-5_33 · Cited by 12
Overcoming Difficulty in Obtaining Dark-skinned Subjects for Remote-PPG by Synthetic AugmentationPreprint
Ba, Y., Wang, Z., Karinca, D., Bozkurt, O. D., & Kadambi, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.06007 · Cited by 16
“Video synthesis, such as deepfakes, has raised public concerns in the community [32].”
BackgroundOn the Truth Claims of Deepfakes: Indexing Images and Semantic Forensics
(2021) · The Journal of Media Art Study and Theory · doi:10.59547/26911566.3.1.04 · Cited by 9
Defending Against Label-Only Attacks via Meta-Reinforcement Learning
Ye, D., Zhu, T., Gao, K., & Zhou, W. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3357292 · Cited by 9
“Several techniques can be used to achieve this, such as fake image detection methods [31], which can distinguish between real and synthesized images.”
Chakraborty, R., & Naskar, R. (2024) · Computer Science Review · doi:10.1016/j.cosrev.2024.100677 · Cited by 20
Spotting the Fakes: A Deep Dive into GAN-Generated Face Detection
Wang, X., Tsai, T. Y., Lin, L., Hui, G., Hu, S., Chang, M., Atrey, P. K., & Lyu, S. (2025) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3742786 · Cited by 12
“Given their potential for misuse, developing reliable detection methods is crucial for maintaining the authenticity and credibility of digital content, especially on social media platforms [32, 71, 106, 161].”
A Decade of Deepfake Research in the Generative AI Era, 2014–2024: A Bibliometric Analysis
Acim, B., Boukhlif, M., Ouhnni, H., Kharmoum, N., & Ziti, S. (2025) · Publications · doi:10.3390/publications13040050 · Cited by 16
Liu, Z., Kou, J., Zhang, W., Gu, C., Fang, X., Huang, Z., Hao, Y., Li, H., Lu, X., Yin, A., et al. (2024) · International Conference on Universal Village (UV) · doi:10.1109/uv63228.2024.11189137 · Cited by 12
Jugade, Y., Syed, Z., Dcosta, C., Panicker, A., & Vora, D. R. (2026) · Discover Applied Sciences · doi:10.1007/s42452-025-08014-w · Cited by 13
“Even though these technologies can be used to create digital content and provide entertainment, their abuse presents significant moral, social, and security issues [18].”
Deep fake videos identification using ANN and LSTM
Tambe, S., Pawar, A., & Yadav, S. K. (2021) · Journal of Discrete Mathematical Sciences and Cryptography · doi:10.1080/09720529.2021.2014140 · Cited by 11
Deepfakes and the promise of algorithmic detectability
Jacobsen, B. N. (2024) · European Journal of Cultural Studies · doi:10.1177/13675494241240028 · Cited by 16
Better Little People Pictures: Generative Creation of Demographically Diverse Anthropographics
Dhawka, P., Perera, L., & Willett, W. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3641957 · Cited by 13
“Additionally, there are ethical concerns [10] surrounding the use of generative models, such as a lack of data agency and privacy, the spread of misinformation via deepfakes [22], human rights concerns around data annotation [38], copyright issues [20], and harmful impacts on artists [17].”
BackgroundDeepfake Technology and Its Implications for Influencer Marketing
Arora, M., Mishra, K. K., Singh, M., Singh, P., & Tripathi, R. (2024) · Advances in information security, privacy, and ethics book series · doi:10.4018/979-8-3693-5298-4.ch005 · Cited by 10
Deepfakes in Social Engineering Attacks
Dsouza, D. S., Hajjar, A. E., & Jahankhani, H. (2024) · Space Law and Policy · doi:10.1007/978-3-031-64045-2_8 · Cited by 14
Deepfakes in Action: Exploring Use Cases Across Industries
Nannaware, S. C., Pillai, R., & Kate, N. T. (2024) · Advances in business information systems and analytics book series · doi:10.4018/979-8-3693-6890-9.ch004 · Cited by 9
Deepfake videos: synthesis and detection techniques – a survey
Saif, S., & Tehsin, S. (2021) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-210625 · Cited by 11
DeepFake and its Enabling Techniques: A Review
Brooks, R., Yuan, Y., Liu, Y., & Chen, H. (2022) · APSIPA Transactions on Signal and Information Processing · doi:10.1561/116.00000024 · Cited by 12
FakePoI: A Large-Scale Fake Person of Interest Video Detection Benchmark and a Strong Baseline
Tian, L., Yao, H., & Li, M. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3269742 · Cited by 11
“In deep learning era [63], [64], [65], [66], [67], [68], [69], [70], there has been an increasing development in deepfake detection [17], [27], [58], [59], [71], [72], [73], [74], [75], [76], [77], [78], [79] because individuals are aware that the abuse of deepfake technology may have a negative…”
BackgroundMethodTenhundfeld, N. L. (2023) · Proceedings of the Human Factors and Ergonomics Society Annual Meeting · doi:10.1177/21695067231192916 · Cited by 11
“There is likely to be an “arms race” between AI generated text and the detection of that text, as has been seen in other advancements like deep-fakes (Mirsky & Lee, 2022), but this technology raises questions about what is an appropriate amount of assistance one can receive in writing.”
BackgroundOn the Generalizability of Two-dimensional Convolutional Neural Networks for Fake Speech Detection
Papastergiopoulos, C., Vafeiadis, A., Papadimitriou, I., Votis, K., & Tzovaras, D. K. (2022) · doi:10.1145/3512732.3533585 · Cited by 10
“Human eyes and ears can be relatively easily fooled by realistic DeepFakes 1 , 2 , while producing DeepFakes is easy with tools such as FaceApp and ZAO.”
BackgroundSoK: How Artificial-Intelligence Incidents Can Jeopardize Safety and Security
May, R., Krüger, J., & Leich, T. (2024) · International Conference on Availability, Reliability and Security (ARES) · doi:10.1145/3664476.3664510 · Cited by 13
“The prevention of a possible system compromise via deep fakes is already being discussed in research, involving several approaches that focus on the effective detection of AI-generated images, audio, or videos [57].”
Deepfake: A Study on Knowledge of Media Practitioners in Cotabato Province, Philippines
Demon, A., & Santos, V. (2025) · Journal of Social Knowledge Education (JSKE) · doi:10.37251/jske.v6i3.1798 · Cited by 8
“As deepfake technologies rapidly evolve, new tools will emerge that may bypass current detection methods, requiring media professionals to stay informed and adaptive [26].”
InfluentialAlkhatib, M. (2025) · Computers · doi:10.3390/computers14110488 · Cited by 10
Husnain, G., Ali, A. B. M., Khan, A., Junaid, A., Usman, M., Awwad, E. M., & Telba, A. A. (2025) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2025.3643884 · Cited by 11
The Security of IP-Based Video Surveillance Systems
Kalbo, N., Mirsky, Y., Shabtai, A., & Elovici, Y. (2020) · Sensors · doi:10.3390/s20174806 · Cited by 102
Self-citationA dual benchmarking study of facial forgery and facial forensics
Pham, T. M., Huynh, T. T., Nguyen, T. T., Nguyen, T. T., Nguyen, T. T., Jo, J., Yin, H., & Nguyen, Q. V. H. (2024) · CAAI Transactions on Intelligence Technology · doi:10.1049/cit2.12362 · Cited by 19
Deepfakes and depiction: from evidence to communication
Pierini, F. (2023) · Synthese · doi:10.1007/s11229-023-04093-7 · Cited by 10
“This kind of application is implemented for instance on shopping websites to virtually try on items (Mirsky & Lee, 2021).”
BackgroundMethodInfluentialOptifake: optical flow extraction for deepfake detection using ensemble learning technique
Vashishtha, S., Gaur, H., Das, U., Sourav, S., Bhattacharjee, E., & Kumar, T. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-18641-x · Cited by 9
OSM-Net: One-to-Many One-Shot Talking Head Generation With Spontaneous Head Motions
Liu, J., Wang, X., Fu, X., Chai, Y., Cai, Y., Dai, J., & Han, J. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3394850 · Cited by 15
“Due to its popularity, the talking head generation task has drawn great attention for a long time [9], [10], [11].”
BackgroundExploring Deepfake Detection: Techniques, Datasets and Challenges
Rana, P., & Bansal, S. R. (2024) · International Journal of Computing and Digital Systems · doi:10.12785/ijcds/160156 · Cited by 11
Kalaimani, G., Kavitha, G., Selvan, C., & Mylapalli, S. (2024) · Signal Image and Video Processing · doi:10.1007/s11760-024-03440-6 · Cited by 8
Image Forgery Localization using Image Patches and Deep Learning
Ali, S. S., Ganapathi, I. I., Vu, N., & Werghi, N. (2022) · IEEE International Conference on Communication Systems and Network Technologies (CSNT) · doi:10.1109/csnt54456.2022.9787662 · Cited by 8
“More details about image forgery detection are given in [12], [23], [29], [34], [35], [38], [40], [47], [49].”
BackgroundDo, T.-L., Tran, M.-K., Nguyen, H. H., & Tran, M. (2022) · SN Computer Science · doi:10.1007/s42979-022-01364-x · Cited by 13
Kraetzer, C., Siegel, D., Seidlitz, S., & Dittmann, J. (2022) · Sensors · doi:10.3390/s22093137 · Cited by 12
“While the detector based on the mouth region showed the best individual results (κ = 0.89) in evaluations, the detectors based on eyes and image foreground (κ = 0.42) also revealed potential for the detection of DeepFakes with (κ = 0.38 and 0.42, respectively).”
BackgroundResultInfluentialPTD: privacy-preserving human face processing framework using tensor decomposition
Kim, J., Tariq, S., & Woo, S. S. (2022) · ACM Symposium on Applied Computing · doi:10.1145/3477314.3507036 · Cited by 10
“Also, survey on different deepfake generation and detection methods are available [44, 64].”
Automated Deepfake DetectionPreprint
Liu, P., Lin, Y., He, Y., Wei, Y., Zhen, L., Zhou, J. T., Goh, R. S. M., & Liu, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.10705 · Cited by 12
“For a systematic review for deepfake generation and detection, please refer to [42].”
BackgroundGenerative adversarial networks in cyber security: Literature review
Arafat, Z., Вадимовна, Ю. О., & Abdulazeez, Z. A. (2025) · Russian Technological Journal · doi:10.32362/2500-316x-2025-13-5-7-24 · Cited by 7
An AI-driven conceptual framework for detecting fake news and deepfake content: a systematic review
Moyo, B. V., Tuyikeze, T., Matsebula, F., & Obagbuwa, I. C. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1737790 · Cited by 11
“This framework extends prior conceptual models (Mirsky and Lee, 2021; Zhou et al., 2019) by explicitly incorporating explainability and feedback dynamics that connect machine learning performance with human trust and policy accountability.”
Daoud, E., Garcia‐Blas, J., Alawadi, S., & Carretero, J. (2026) · Progress in Artificial Intelligence · doi:10.1007/s13748-026-00448-6 · Cited by 9
“These technologies can mimic a victim’s voice or facial features to deceive others [61, 169–171].”
Deepfakes na perspectiva da semiótica
de Souza, C. E., & Santaella-Braga, L. (2021) · TECCOGS Revista Digital de Tecnologias Cognitivas · doi:10.23925/1984-3585.2021i23p26-44 · Cited by 7
Vijaya, J., Kazi, A. A., Mishra, K. G., & Praveen, A. (2023) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt56998.2023.10307811 · Cited by 9
Assessing the Human Ability to Recognize Synthetic Speech in Ordinary Conversation
Prudký, D., Firc, A., & Malinka, K. (2023) · International Conference of the Biometrics Special Interest Group (BIOSIG) · doi:10.1109/biosig58226.2023.10346006 · Cited by 13
“Mirsky and Lee [1] define a deepfake simply as a ”Believ-able media generated by a deep neural network.””
BackgroundAnonymizing eye-tracking stimuli with stable diffusion
Kurzhals, K. (2024) · Computers & Graphics · doi:10.1016/j.cag.2024.103898 · Cited by 7
A Lightweight CNN for Efficient Deepfake Detection of Low-resolution Images in Frequency Domain
Sabareshwar, D., Raghul, S., Ravi, S., Varalakshmi, M., & U, P. M. P. (2024) · International Conference on Emerging Trends in Information Technology and Engineering (ICETITE) · doi:10.1109/ic-etite58242.2024.10493406 · Cited by 12
“Different algorithms are used for the generation and detection of deepfakes [6]-[8].”
MethodDesigning a Safe Ecosystem to Prevent Deepfake-Driven Misinformation on Elections
Kumar, B. P., Ahmed, M., & Sadanandam, M. (2024) · Digital Society · doi:10.1007/s44206-024-00107-0 · Cited by 10
“There are several techniques for creating deepfake software using machine learning algorithms (Mirsky & Lee, 2021).”
A deep dive into enhancing sharing of naturalistic driving data through face deidentification
Thapa, S., & Sarkar, A. (2024) · The Visual Computer · doi:10.1007/s00371-024-03552-7 · Cited by 9
Open-Set Synthesis for Free-Viewpoint Human Body Reenactment of Novel Poses
Sheng, Z., Liu, F., Liu, M., Zheng, F., & Nie, L. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3434733 · Cited by 13
“Single-viewpoint body reenactment generates a video of a source subject replicating the movements of a source pose from a source video clip [1], [22].”
Beyond the Screen: Evaluating Deepfake Detectors under Moiré Pattern Effects
Tariq, R., Heo, M., Woo, S. S., & Tariq, S. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00446 · Cited by 14
“Yet, as detection methods become more advanced, so too do the techniques for creating deepfakes [37, 55], perpetuating a cycle of technological escalation.”
Hanae, A., Saida, E. M., & Gahi, Y. (2024) · International Conference on Future Internet of Things and Cloud (FiCloud) · doi:10.1109/ficloud62933.2024.00052 · Cited by 8
SpecViT: A Custom Vision-Transformer based Approach for Audio Deepfake Detection
Modak, S., Das, A. K., & Naskar, R. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10889022 · Cited by 12
“…which collectively refers to a set of sophisticated digital media generation and manipulation techniques, employing deep learning algorithms and advanced artificial intelligence, now poses a major threat due to its potential for misuse towards deception and misleading of viewers [35], [25], [26].”
DeepFN: Towards Generalizable Facial Action Unit Recognition with Deep Face Normalization
Hernandez, J., McDuff, D., Rudovic, O. O., Fung, A., & Czerwinski, M. P. (2022) · International Conference on Affective Computing and Intelligent Interaction and workshops · doi:10.1109/acii55700.2022.9953868 · Cited by 8
“Some of the most popular methods for facial expression transfer and expression synthesis start by detecting facial landmarks or action units to help guide the transfer process (e.g., [46], [47], [48], [49], [50]).”
BackgroundDo, T.-L., Tran, M.-K., Nguyen, H. H., & Tran, M. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-91387-8_19 · Cited by 10
Employing Super Resolution to Improve Low-Quality Deepfake Detection
Perera, A. S., Atukorale, A. S., & Kumarasinghe, P. (2022) · International Conference on Advances in ICT for Emerging Regions · doi:10.1109/icter58063.2022.10024088 · Cited by 9
“Hence, the authors trained DNNs as a generic classifier and let the model decide suitable features undirectedly [2].”
BackgroundMethodInfluentialVerifiable Privacy-Enhanced Rotation Invariant LBP Feature Extraction in Fog Computing
Bian, M., Liu, J. K., Sun, S.-F., Zhang, X., & Ren, Y. (2023) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2023.3246992 · Cited by 7
Mishra, A., Bharwaj, A., Yadav, A. K., Batra, K., & Mishra, N. (2024) · International Conference on Cloud Computing, Data Science & Engineering (Confluence) · doi:10.1109/confluence60223.2024.10463337 · Cited by 15
Sun, Y., Zhang, Z., Qiu, C., Wang, L., Sun, L., & Wang, Z. (2022) · International Conference on Intelligent Computing and Signal Processing (ICSP) · doi:10.1109/icsp54964.2022.9778420 · Cited by 11
“In order to prevent the excessive proliferation of forgery videos and cause people’s trust crisis in the media, the corresponding detection methods have been gradually proposed [25, 28, 29, 41].”
MethodNarayanan, V., Robertson, B. W., Hickerson, A., Srivastava, B., & Smith, B. W. (2021) · IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA) · doi:10.1109/tpsisa52974.2021.00053 · Cited by 11
Leveraging High-Frequency Components for Deepfake Detection
Mejri, N., Papadopoulos, K., & Aouada, D. (2021) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp53017.2021.9733606 · Cited by 11
“This section examines important works addressing deep-fake detection using color images and approaches leveraging frequency-domain features for the same task. a) RGB image-based deepfake detection : RGB-image-based detectors exist for both artifact-specific and undirected deepfake detectors [7].”
BackgroundAttention-based Multimodal learning framework for Generalized Audio-Visual Deepfake Detection
Masood, M., Javed, A., & Irtaza, A. (2023) · Preprint (Research Square) · doi:10.21203/rs.3.rs-3415144/v1 · Cited by 6
Temmermans, F., Caldwell, S., Papadopoulos, S., Pereira, F., & Rixhon, P. (2023) · 2023 24th International Conference on Digital Signal Processing (DSP) · doi:10.1109/dsp58604.2023.10167884 · Cited by 6
“While there is a rapidly growing body of research dedicated to the detection of synthetic manipulations, commonly referred to as deepfake detection [5]–[7], there are similar challenges, as in the case of media forensics analysis, when trying to assess the authenticity of media and to establish…”
BackgroundA survey on deep learning based reenactment methods for deepfake applications
Dhanyalakshmi, R., Popirlan, C. I., & Hemanth, D. J. (2024) · IET Image Processing · doi:10.1049/ipr2.13201 · Cited by 9
Jääskeläinen, P., Sanchez, C., & Holzapfel, A. (2025) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3715275.3732011 · Cited by 8
Face Swap Detection: A Systematic Literature Review
Hriez, S. (2025) · IEEE Access · doi:10.1109/access.2025.3598980 · Cited by 8
“On the other hand, the authors of [11] provide an in-depth exploration of deepfake technology, detailing both its creation and detection methods.”
Łabuz, M., & Soczyński, S. (2025) · Technology in Society · doi:10.1016/j.techsoc.2025.103060 · Cited by 6
ERF-BA-TFD+: a multimodal model for audio-visual deepfake detection
Wang, L., Zhao, J. Q., Zhang, X., Guo, X., Yuan, Y., Zhang, T., Chu, J., Jiang, Y., Yang, X., Jin, L., et al. (2025) · Vicinagearth. · doi:10.1007/s44336-025-00021-0 · Cited by 9
“Deepfake attacks, which involve the synthetic generation or manipulation of audio and video, pose significant threats to trustworthiness in digital media.”
‘It's still abuse’: community attitudes and perceptions on AI-generated image-based sexual abuse
Henry, N., Umbach, R., Shelby, R. M., Beard, G., & Given, L. M. (2026) · Information Communication & Society · doi:10.1080/1369118x.2026.2613437 · Cited by 10
“Deepfakes are synthetic media generated using sophisticated AI tools that produce highly realistic fake content of a real, identifiable person with minimal input data (Mirsky & Lee, 2021), often requiring only a single image or a few seconds of audio.”
Interpol review of forensic video analysis, 2019–2022
Geradts, Z., & Riphagen, Q. (2023) · Forensic Science International Synergy · doi:10.1016/j.fsisyn.2022.100309 · Cited by 11
“These methods therefore do not make any assumptions as to which attack could be used, making it more suitable as a general model to detect unknown creation methods [36].”
InfluentialOn Using rPPG Signals for DeepFake Detection: A Cautionary Note
D’Amelio, A., Lanzarotti, R., Patania, S., Grossi, G., Cuculo, V., Valota, A., & Boccignone, G. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43153-1_20 · Cited by 13
Personal Rights and Intellectual Properties in the Upcoming Era: The Rise of Deepfake Technologies
Hasani, A., Rasheed, J., Alsubai, S., & Luma-Osmani, S. (2024) · Lecture notes in networks and systems · doi:10.1007/978-3-031-62881-8_32 · Cited by 6
Kalyanasundaram, P., Priya, K., Kavinkumar, S., Gopinath, G., & Bommi, S. T. K. (2024) · doi:10.1109/icstem61137.2024.10561029 · Cited by 6
Learning Meta Model for Strong Generalization Deepfake Detection
Huang, D., & Zhang, Y. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10651482 · Cited by 6
Assess and Guide: Multi-modal Fake News Detection via Decision Uncertainty
Wu, J., Xu, D., Liu, W., Zhou, J., Ong, Y., Hu, S.-Y., Zhu, H.-Y., & Wang, Z. (2024) · Proceedings of the 1st ACM Multimedia Workshop on Multi-modal Misinformation Governance in the Era of Foundation Models · doi:10.1145/3689090.3689389 · Cited by 8
Collaboration and Collective Action: Addressing the Deepfake Challenge as a Community
Subrahmanyam, S. (2024) · Advances in business information systems and analytics book series · doi:10.4018/979-8-3693-6890-9.ch007 · Cited by 7
Financial Fraud and Manipulation: The Malicious Use of Deepfakes in Business
Kaushik, P., Garg, V., Priya, A., & Kant, S. (2024) · Advances in business information systems and analytics book series · doi:10.4018/979-8-3693-6890-9.ch008 · Cited by 18
Eerie edibles: Realism and food neophobia predict an uncanny valley in AI-generated food images
Diel, A., Lalgi, T. J., Teufel, M., Bäuerle, A., & MacDorman, K. F. (2025) · Appetite · doi:10.1016/j.appet.2025.107926 · Cited by 8
“The most convincing AI-generated media content is indistinguishable from real its counter-parts (Brey et al., 2023; Diel et al., 2024; Groh, Epstein, Firestone, & Picard, 2022; Mirsky & Lee, 2021).”
Media Forensics and Deepfake-Systematic Survey
Nadeem Jabbar, C. H., Saghir, A., Meer, A. A., Sahi, S., Hassan, B., & Yasir, S. M. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-77617-5_24 · Cited by 6
Ognibene, D., Donabauer, G., Theophilou, E., Buršić, S., Lomonaco, F., Wilkens, R., Hernández‐Leo, D., & Kruschwitz, U. (2023) · Datenbank-Spektrum · doi:10.1007/s13222-023-00436-3 · Cited by 8
Deepfake detection based on remote photoplethysmography
Xu, Q., Qiao, H., Liu, S., & Liu, S. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-14744-z · Cited by 11
Call of the Wild Web: Comparing Parrot Engagement in Live vs. Pre-Recorded Video Calls
Hirskyj-Douglas, I., Cunha, J. M., & Kleinberger, R. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3641938 · Cited by 6
Towards Generalized Detection of Face-Swap Deepfake Images
Ghasemzadeh, F., Moghaddam, T., Dai, J., Yun, J., & Kim, D. S. (2024) · doi:10.1145/3660354.3660359 · Cited by 11
“Face-swap deepfakes are generally created through variations or combinations of generative and encoder-decoder networks [16].”
BackgroundMethodInfluentialDeep Learning for Fake News Detection
Kumar, G. S. (2020) · The information retrieval series · doi:10.1007/978-3-030-62696-9_4 · Cited by 9
Immersive Traditional Chinese Portrait Painting: Research on Style Transfer and Face Replacement
Li, J., Wang, Q., Li, S., Zhong, Q., & Zhou, Q. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-88007-1_16 · Cited by 6
Can Deepfakes be created on a whim?
Mehta, P., Jagatap, G., Gallagher, K., Timmerman, B., Deb, P., Garg, S., Greenstadt, R., & Dolan-Gavitt, B. (2023) · Companion Proceedings of the ACM Web Conference 2023 · doi:10.1145/3543873.3587581 · Cited by 5
A novel approach to identify deepfake text using social media data
Devi, B. T., & Rajasekaran, R. (2025) · Social Network Analysis and Mining · doi:10.1007/s13278-025-01536-6 · Cited by 6
“A comprehensive investigation was carried out in a survey (Mirsky and Lee 2021) to analyze the advancements, trends, and limitations in identifying deepfakes.”
Cassia, M., Guarnera, L., Casu, M., Zangara, I., & Battiato, S. (2025) · IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering (MetroXRAINE) · doi:10.1109/metroxraine66377.2025.11340536 · Cited by 11
“These issues have become increasingly urgent as the digital forensics and legal communities confront the implications of synthetic media, including intellectual property disputes, unauthorized use of personal images, and breaches of data protection regulations [8], [9].”
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.