Deepfakes generation and detection: state-of-the-art, open challenges, countermeasures, and way forward
Open accessThe DOI matches its Crossref record; 354 of the 354 references it cites were found in a registry or an index.
Abstract
Easy access to audio-visual content on social media, combined with the availability of modern tools such as Tensorflow or Keras, and open-source trained models, along with economical computing infrastructure, and the rapid evolution of deep-learning (DL) methods have heralded a new and frightening trend. Particularly, the advent of easily available and ready to use Generative Adversarial Networks (GANs), have made it possible to generate deepfakes media partially or completely fabricated with the intent to deceive to disseminate disinformation and revenge porn, to perpetrate financial frauds and other hoaxes, and to disrupt government functioning. Existing surveys have mainly focused on the detection of deepfake images and videos; this paper provides a comprehensive review and detailed analysis of existing tools and machine learning (ML) based approaches for deepfake generation, and the methodologies used to detect such manipulations in both audio and video. For each category of deepfake, we discuss information related to manipulation approaches, current public datasets, and key standards for the evaluation of the performance of deepfake detection techniques, along with their results. Additionally, we also discuss open challenges and enumerate future directions to guide researchers on issues which need to be considered in order to improve the domains of both deepfake generation and detection. This work is expected to assist readers in understanding how deepfakes are created and detected, along with their current limitations and where future research may lead.
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
“In the following years, developments such as realistic lip-syncing, voice cloning, and the creation of full-body deepfakes were undertaken (Masood etal. 2023).”
From Deepfake video detection: challenges and opportunities (2024) · cites this paper as Masood et al. 2023
In the citing paper
“only three of them (Heidari et al., 2023; Khanjani et al., 2023; Masood et al., 2023) mentioned audio datasets.”
From Deepfake: definitions, performance metrics and standards, datasets, and a meta-review (2024) · cites this paper as Masood et al., 2023
In the citing paper
“Lyu (2020) and Masood et al. (2023) also suggested that we need to consider social media laundering effects in training data and improve the evaluation of datasets.”
From Deepfake: definitions, performance metrics and standards, datasets, and a meta-review (2024) · cites this paper as Masood et al., 2023
In the citing paper
“The main presumption in most cases in underlying existing deepfake video detection techniques is that only the visual signal in a video contains fake content [5].”
From Attention-based Multimodal learning framework for Generalized Audio-Visual Deepfake Detection (2023) · cites this paper as [5]
In the citing paper
“Additionally, they are frequently susceptible to common perturbations like compression, making them vulnerable to image-processing pipelines on social networks [5].”
From Attention-based Multimodal learning framework for Generalized Audio-Visual Deepfake Detection (2023) · cites this paper as [5]
4 more claims about this paper
Create a free account to see every claim other papers make about this one.
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 3×
“More specifically, they considered two GAN frameworks, namely StarGAN [36] and GauGAN [175].”
MethodAuto-Encoding Variational Bayes
Kingma, D. P., & Welling, M. (2013) · arXiv · doi:10.48550/arxiv.1312.6114 · Cited by 20,067
GAN(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
FaceNet: A unified embedding for face recognition and clustering
Schroff, F., Kalenichenko, D., & Philbin, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298682 · Cited by 15,267
Unsupervised representation learning with deep convolutional generative adversarial networks
Radford, A., Metz, L., & Chintala, S. (2015) · arXiv · doi:10.48550/arxiv.1511.06434 · Cited by 12,235 · cited 3×
“DCGAN [143] was the first approach that introduced a deconvolution layer in the generator to replace the fully connected layer, which achieved better performance in synthetic image generation.”
BackgroundMethodA Style-Based Generator Architecture for Generative Adversarial Networks
Karras, T., Laine, S., & Aila, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00453 · Cited by 11,714 · cited 7×
“Compared to [51, 96, 97], StyleGAN [99] achieved state-of-the-art high resolution in the generated images i.”
BackgroundInfluential2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
(2017) · doi:10.1109/cvpr35066.2017 · Cited by 7,141
Analyzing 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
Analyzing 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
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
Research works printed but not linked: 22
- Goodfellow I et al (2014) Generative adversarial nets. Adv Neural Inf Proces Syst 1:2672–2680
- Chesney R, Citron D (2019) Deepfakes and the new disinformation war: the coming age of post-truth geopolitics. Foreign Aff 98:147
- Chesney B, Citron D (2019) Deep fakes: a looming challenge for privacy, democracy, and national security. Calif Law Rev 107:1753
- Gupta S, Mohan N, Kaushal P (2021) Passive image forensics using universal techniques: a review. Artif Intell Rev 1:1–51
- Soukupova T, Cech J (2016) Eye blink detection using facial landmarks. In: 21st Computer Vision Winter Workshop
- Korshunov P et al. (2019) Tampered speaker inconsistency detection with phonetically aware audio-visual features. In: International Conference on Machine Learning · DOI · Paper page
- Thies J, Zollhöfer M, Theobalt C, Stamminger M, Nießner M (2018) Headon: real-time reenactment of human portrait videos. ACM Trans Graph 37:1–13
- Mirza M, Osindero S (2014) Conditional generative adversarial nets. arXiv preprint arXiv:14111784
- Nawaz M, Mehmood Z, Nazir T, Masood M, Tariq U, Mahdi Munshi A, Mehmood A, Rashid M (2021) Image authenticity detection using DWT and circular block-based LTrP features. Comput Mater Contin 69:1927–1944
- Nataraj L, Mohammed TM, Manjunath B, Chandrasekaran S, Flenner A, Bappy JH, Roy-Chowdhury AK (2019) Detecting GAN generated fake images using co-occurrence matrices. Electron Imaging 2019:532-531–532-537
- Ping W et al (2018) Deep voice 3: 2000-speaker neural text-to-speech. Proc ICLR:214–217
- Bińkowski M et al. (2020) High fidelity speech synthesis with adversarial networks. Paper presented at the 8th international conference on learning representations
- Kumar K et al (2019) Melgan: generative adversarial networks for conditional waveform synthesis. Adv Neural Inf Proces Syst 32
- Kong J, Kim J, Bae J (2020) Hifi-Gan: generative adversarial networks for efficient and high fidelity speech synthesis. Adv Neural Inf Proces Syst 33:17022–17033
- Peng K, Ping W, Song Z, Zhao K (2020) Non-autoregressive neural text-to-speech. In: International conference on machine learning. PMLR, pp 7586–7598
- Kim J, Kim S, Kong J, Yoon S (2020) Glow-tts: a generative flow for text-to-speech via monotonic alignment search. Adv Neural Inf Proces Syst 33:8067–8077
- Ren Y, Ruan Y, Tan X, Qin T, Zhao S, Zhao Z, Liu T-Y (2019) Fastspeech: fast, robust and controllable text to speech. Adv Neural Inf Proces Syst 32:3165–3174
- Malik H (2019) Fighting AI with AI: fake speech detection using deep learning. In: International Conference on Audio Forensics. AES
- Khochare J, Joshi C, Yenarkar B, Suratkar S, Kazi F (2021) A deep learning framework for audio deepfake detection. Arab J Sci Eng 1:1–12
- Frank J, Schönherr L (2021) WaveFake: a data set to facilitate audio deepfake detection. In: 35th annual conference on neural information processing systems
- Huang Y et al. (2020) FakeRetouch: evading DeepFakes detection via the guidance of deliberate noise. arXiv preprint arXiv:09213
- Wodajo D, Atnafu S (2021) Deepfake video detection using convolutional vision transformer. arXiv preprint arXiv:11126
Cited by
DeepFake Detection for Human Face Images and Videos: A Survey
Malik, A., Kuribayashi, M., Abdullahi, S. M., & Khan, A. N. (2022) · IEEE Access · doi:10.1109/access.2022.3151186 · Cited by 297
Deepfake video detection: challenges and opportunities
Kaur, A., Noori Hoshyar, A., Saikrishna, V., Firmin, S., & Xia, F. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10810-6 · Cited by 214
“Deepfakes are intended for use on social media platforms, where conspiracies, rumours, and misinformation spread quickly because users tend to follow what is trending (Masood et al. 2023).”
InfluentialShoaib, M. R., Wang, Z., Ahvanooey, M. T., & Zhao, J. (2023) · 2023 International Conference on Computer and Applications (ICCA) · doi:10.1109/icca59364.2023.10401723 · Cited by 202
Ilyas, H., Javed, A., & Malik, K. M. (2023) · Applied Soft Computing · doi:10.1016/j.asoc.2023.110124 · Cited by 186
Self-citationDeepfake generation and detection: Case study and challenges
Patel, Y., Tanwar, S., Gupta, R., Bhattacharya, P., Davidson, I. E., Nyameko, R., Aluvala, S., & Vimal, V. (2023) · IEEE Access · doi:10.1109/access.2023.3342107 · Cited by 186
Metadata
- Authors
- Masood, M., Nawaz, M., Malik, K. M., Javed, A., Irtaza, A., & Malik, H.
- Affiliations
- University of Engineering and Technology Taxila (PK)
- Oakland University (US)
- University of Michigan–Dearborn (US)
- Corresponding author
- Malik, Khalid Mahmood
- Venue
- Applied Intelligence
- Published
- 2022-06-04
- Volume
- 53
- Issue
- 4
- Pages
- 3974-4026
- ISSN
- 0924-669X (ISSN-L)
- 1573-7497
- OpenAlex
- W3135809943
- Cited by
- 543
- References
- 345
- Citations by year
- 2026: 121 · 2025: 164 · 2024: 140 · 2023: 82 · 2022: 25
- FWCI
- 33.62
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- www.springernature.com/gp/researchers/text-and-data-mining (tdm)
- www.springernature.com/gp/researchers/text-and-data-mining (vor)
- Locations
- Applied Intelligence (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation (1815724)
- Punjab Higher Education Commission, Pakistan (PHEC/ARA/PIRCA/20527/21)
- Michigan Translational Research and Commercialization (292883)
- 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, disinformation, revenge porn, deepfake datasets, evaluation standards, countermeasures, hoaxes
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: Deepfakes generation and detection: state-of-the-art, open challenges, countermeasures, and way forward. https://app.cochat.ai/papers/10.1007/s10489-022-03766-z
- The paper
- Masood, M., Nawaz, M., Malik, K. M., Javed, A., Irtaza, A., & Malik, H. (2023). Deepfakes generation and detection: state-of-the-art, open challenges, countermeasures, and way forward. Applied Intelligence. https://doi.org/10.1007/s10489-022-03766-z
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.