Deepfake Attacks: Generation, Detection, Datasets, Challenges, and Research Directions
Open accessThe DOI matches its Crossref record; 125 of the 126 references it cites were found in a registry or an index, and 1 are not checked yet; 3 of the 86 sources its claims cite were checked for support.
Abstract
Recent years have seen a substantial increase in interest in deepfakes, a fast-developing field at the nexus of artificial intelligence and multimedia. These artificial media creations, made possible by deep learning algorithms, allow for the manipulation and creation of digital content that is extremely realistic and challenging to identify from authentic content. Deepfakes can be used for entertainment, education, and research; however, they pose a range of significant problems across various domains, such as misinformation, political manipulation, propaganda, reputational damage, and fraud. This survey paper provides a general understanding of deepfakes and their creation; it also presents an overview of state-of-the-art detection techniques, existing datasets curated for deepfake research, as well as associated challenges and future research trends. By synthesizing existing knowledge and research, this survey aims to facilitate further advancements in deepfake detection and mitigation strategies, ultimately fostering a safer and more trustworthy digital environment.
Verified 2026-11-19 · 1 reference not checked yet
Overview
CoChat Summary
TL;DR
This survey reviews deepfake generation techniques, detection clues and deep learning architectures, datasets, and open challenges. It synthesizes state-of-the-art methods and reports benchmark performance and dataset characteristics, while noting real-time detection, generalization, interpretability, privacy, dataset quality, and adversarial perturbations as key unresolved issues.
Key findings
- The paper identifies five primary deepfake manipulation types: face synthesis, attribute manipulation, identity swap/face swapping, face reenactment, and lip-syncing.
- Detection approaches are organized by clues: spatial artifacts, biological/physiological signs, audio-visual inconsistencies, convolutional traces, identity information, facial emotions, temporal inconsistencies, and spatial-temporal features.
- Reported detection performance examples include Zhao et al. with ACC = 99.8 on Celeb-DF and ACC = 92.1 on DFDC; Wang, J. et al. with ACC = 97.93 and AUC = 99.51 on FF++(HQ) and AUC = 99.80 on Celeb-DF; and Chen et al. with Celeb-DF AUC = 99.80 and FF++ AUC = 99.39.
- Dataset examples include DFDC with over 100,000 total clips from 3426 paid actors, Celeb-DF with 590 real and 5639 fake videos, KoDF with 62,166 authentic and 175,776 fake videos, and ForgeryNet with 2.9 million images, 221,247 videos, and 15 manipulation methods.
Methods
- Design: narrative literature survey/review; the paper states that no new data were created or analyzed.
- Scope: covers deepfake manipulation types, generation techniques such as GANs and autoencoders, detection clues and deep learning models, existing datasets, and challenges/future research directions.
- Analysis: synthesizes existing knowledge and tabulates recent detection models with features, techniques, datasets, and intra-dataset performance (Table 2), plus key characteristics of prominent deepfake datasets (Table 3).
Limitations
- The paper states field-level challenges: real-time detection, generalization and robustness under compression/noise, lack of interpretability, privacy concerns, dataset quality and visual differences from online deepfakes, and adversarial perturbations.
- Text makes evident: as a survey, it provides no new experiments or empirical validation; reported performance numbers are compiled from cited works and not independently reproduced.
- No explicit limitations of the survey itself are stated in the paper.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures






Verification
Claims the paper makes
3 Valid · 0 Not valid · 68 Not checked · 25 Own results and interpretations
Every source the paper cites for this claim was checked and supports it.
In the paper
“DeeperForensics-1.0 [126] is a significant dataset available for detecting deepfakes that contains 50,000 original clips and 10,000 forged ones.”
§ Review Deepfake Attacks: Generation, Detection, Datasets, Challenges, and Research Directions > 5. Datasets
What the sources say
- Supportedcites [126] Jiang, L., Li, R., Wu, W., Qian, C., and Loy, C.C. (2020, January 13–19). DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA. source
Section 3 (p. 3) of our copy states DeeperForensics-1.0 'consists of 60,000 videos with 17.6 million frames in total, including 50,000 original collected videos and 10,000 manipulated videos', which matches the claimed split exactly. The Abstract (p. 1) corroborates the 60,000-video total, and the Introduction (p. 1) repeats the dataset composition. (LLM, conf=0.95)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
None of the sources cited for this claim have been checked yet.
In the paper
“There exist five primary types of deepfake manipulation, as shown in Figure 1.”
§ Review Deepfake Attacks: Generation, Detection, Datasets, Challenges, and Research Directions > 3.1. Deepfake Manipulation Types
What the sources say
- Not checked yetcites [32] Shi, Y., Liu, X., Wei, Y., Wu, Z., and Zuo, W. (2022, January 18–24). Retrieval-Based Spatially Adaptive Normalization for Semantic Image Synthesis. Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA. source
- Not checked yetcites [33] Liu, M., Ding, Y., Xia, M., Liu, X., Ding, E., Zuo, W., and Wen, S. (2019, January 15–20). STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA. source
- Not checked yetcites [34] Li, L., Bao, J., Yang, H., Chen, D., and Wen, F. (2020). FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping. arXiv.
- Not checked yetcites [35] (2023, July 18). Robust and Real-Time Face Swapping Based on Face Segmentation and CANDIDE-3. Available online: https://www.springerprofessional.de/robust-and-real-time-face-swapping-based-on-face-segmentation-an/15986368.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“Deepfakes can be used for entertainment, education, and research; however, they pose a range of significant problems across various domains, such as misinformation, political manipulation, propaganda, reputational damage, and fraud.”
§ Review Deepfake Attacks: Generation, Detection, Datasets, Challenges, and Research Directions > Abstract
What the sources say
- Not checked yetcites [1] Hancock, 2021, The Social Impact of Deepfakes, Cyberpsychol. Behav. Soc. Netw. source
- Not checked yetcites [2] Giansiracusa, N. (2021). How Algorithms Create and Prevent Fake News: Exploring the Impacts of Social Media, Deepfakes, GPT-3, and More, Apress. source
- Not checked yetcites [3] Fallis, 2021, The Epistemic Threat of Deepfakes, Philos. Technol. source
- Not checked yetcites [4] Karnouskos, 2020, Artificial Intelligence in Digital Media: The Era of Deepfakes, IEEE Trans. Technol. Soc. source
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“Moreover, there is RSGAN [46], which can encode the appearances of faces and hair into underlying latent space representations, enabling the image appearances to be modified by manipulating the representations in the latent spaces.”
§ Review Deepfake Attacks: Generation, Detection, Datasets, Challenges, and Research Directions > 3.2. Deepfake Generation Techniques
What the sources say
- Not checked yetcites [46] Natsume, R., Yatagawa, T., and Morishima, S. (2018, January 12). RSGAN: Face Swapping and Editing Using Face and Hair Representation in Latent Spaces. Proceedings of the ACM SIGGRAPH 2018 Posters, Vancouver, BC, Canada. source
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“By directing the model's focus toward relevant features and regions of the input data, attention mechanisms enhance the model's discriminative power and improve its overall accuracy.”
§ Review Deepfake Attacks: Generation, Detection, Datasets, Challenges, and Research Directions > 4.2. Deep Learning Models for Deepfake Detection
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
16 more claims
Create a free account to see all 96 claims and to verify the 83 references still open.
- Probably not a substantial claim. 66
- It may state two separate claims as one. 29
- The quote only partly states this claim. 1
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
“These refinements ensure superior detection performance in resource-constrained environments, making EfficientNetB4-Lite an ideal solution for deployment on edge devices without compromising performance [27].”
From FL-TENB4: A Federated-Learning-Enhanced Tiny EfficientNetB4-Lite Approach for Deepfake Detection in CCTV Environments (2025) · cites this paper as [27]
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
“Conventional deep learning models often prioritize accuracy at the expense of computational feasibility, making them unsuitable for resource-limited edge devices.”
From FL-TENB4: A Federated-Learning-Enhanced Tiny EfficientNetB4-Lite Approach for Deepfake Detection in CCTV Environments (2025) · cites this paper as [27]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Deepfake generation involves the use of advanced generative models to imitate genuine content. This poses difficulties for standard methods that may have trouble adjusting to the complex patterns present in synthetic media (Naitali etal. 2023).”
From Deepfake video detection: challenges and opportunities (2024) · cites this paper as Naitali et al. 2023
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Review Deepfake Attacks: Generation, Detection, Datasets, Challenges, and Research Directions > 5. Datasets
“DeeperForensics-1.0 [126] is a significant dataset available for detecting deepfakes that contains 50,000 original clips and 10,000 forged ones.”
§ Review Deepfake Attacks: Generation, Detection, Datasets, Challenges, and Research Directions > 7. Conclusions
“| DeeperForensics-1.0 [126] | 2020 | 48,475 | 11,000 | DF-VAE [126] | Visual |”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Review Deepfake Attacks: Generation, Detection, Datasets, Challenges, and Research Directions > 5. Datasets
“It includes 3000 edited videos in addition to 1000 original videos that were pulled from the YouTube-8M dataset.”
§ Review Deepfake Attacks: Generation, Detection, Datasets, Challenges, and Research Directions > 7. Conclusions
“| FaceForensics ++ [118] | 2019 | 1000 | 4000 | DeepFakes [119], Face2Face2 [37], FaceSwap [120], NeuralTextures [121], FaceShifter [34] | Visual |”
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
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
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.11929 · Cited by 47,472
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00986 · Cited by 35,534
Unpaired image-to-image translation using cycle-consistent adversarial networks
Zhu, J.-Y., Park, T., Isola, P., & Efros, A. A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.244 · Cited by 23,602
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
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
Ledig, C., Theis, L., Huszar, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., Wang, Z., et al. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.19 · Cited by 12,696
A 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
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
Research works printed but not linked: 10
- Kandari, M., Tripathi, V., and Pant, B. (2023, January 15–17). A Comprehensive Review of Media Forensics and Deepfake Detection Technique. Proceedings of the 2023 10th International Conference on Computing for Sustainable Global Development (INDIACom), New Delhi, India.
- Prajwal, K.R., Mukhopadhyay, R., Philip, J., Jha, A., Namboodiri, V., and Jawahar, C.V. (2019). Proceedings of the 27th ACM International Conference on Multimedia, Nice, France, 15 October 2019, Association for Computing Machinery.
- Hu, J., Liao, X., Gao, D., Tsutsui, S., Qin, Z., and Shou, M.Z. (2023). DeepfakeMAE: Facial Part Consistency Aware Masked Autoencoder for Deepfake Video Detection. arXiv.
- Wang, J., Wu, Z., Ouyang, W., Han, X., Chen, J., Lim, S.-N., and Jiang, Y.-G. (2022). Proceedings of the ICMR—International Conference on Multimedia Retrieval, Newark, NJ, USA, 27–30 June 2022, Association for Computing Machinery, Inc.
- Cai, Z., Stefanov, K., Dhall, A., and Hayat, M. (December, January 30). Do You Really Mean That? Content Driven Audio-Visual Deepfake Dataset and Multimodal Method for Temporal Forgery Localization: Anonymous Submission Paper ID 73. Proceedings of the International Conference on Digital Image Computing: Techniques and Applications, DICTA, Sydney, Australia.
- Tan, M., and Le, Q.V. (2020). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks, PMLR.
- Yan, Z., Sun, P., Lang, Y., Du, S., Zhang, S., and Wang, W. (2022). Landmark Enhanced Multimodal Graph Learning for Deepfake Video Detection. arXiv.
- Dolhansky, B., Bitton, J., Pflaum, B., Lu, J., Howes, R., Wang, M., and Ferrer, C.C. (2020). The DeepFake Detection Challenge (DFDC) Dataset. arXiv.
- Khalid, H., Tariq, S., and Woo, S.S. (2021). FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset. arXiv.
- Korshunov, P., and Marcel, S. (2018). DeepFakes: A New Threat to Face Recognition? Assessment and Detection. arXiv.
Cited by
Items 101–114 of 114
Wei, W. C. T., & Teo, J. (2025) · International Conference on Computer and Communication Engineering · doi:10.1109/iccce66530.2025.11474034
Visual Forensics of Deepfake Images: Manual Detection and Classification of Visual Artifacts
Malik, A., Sweshika, M., Pooja, M., Rao, G. D. R. R. G. D. R., & Kumari, K. (2025) · Journal of Punjab Academy of Forensic Medicine & Toxicology · doi:10.5958/0974-083x.2025.00042.7
MSF-RGBNet: A Lightweight Multi-Stage Fusion Architecture for Deepfake Image Detection
Roy, P., & Roy, P. (2025) · International Conference on Computer and Information Technology (ICCIT) · doi:10.1109/iccit68739.2025.11491195
Deepfake Forensics: Threats and Detection of AI-Manipulated Media
Cardoso, P. M. C., Oliveira, R. S., Gomes, T. F. N., Bastos, E. S., & Lopes, S. F. S. F. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-7660-8.ch015 · Cited by 1
SF-ViT: Harnessing Complementary Spatial and Spectral Representations for Robust Deepfake DetectionPreprint
Ramteke, K., & Chaudhari, A. Y. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6916027
Hussien, J. A., Morsy, M. A., Mahdy, R. S., Zakaria, R. A., & Ata, M. M. (2026) · ICEENG International Conference for Innovations in Intelligent Computing and Cybersecurity (IICC) · doi:10.1109/iicc69623.2026.11582836
A Novel Framework for Fake Visual Content Detection Through Hybrid Intelligent Techniques
Vaghela, V., Sadaria, P., & Ranpara, R. D. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-08600-6_7
Evaluation of methods for intellectual analysis of manipulative content in the information space
Senkivskyy, V., Iryna, P. I. K. H., Kudriashova, A. V., ANDRIIV, R., & Senkivskyy, N. (2025) · International Workshop on Intelligent Information Technologies & Systems of Information Security (IntelITSIS) · doi:10.55056/ceur-ws.org/vol-3963/paper12.pdf · Cited by 3
Bhattacharya, A. K., & Sharma, S. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-2600-2977-0.ch010
Spatial-Frequency Wavelet Analysis for Synthetic Face Image Detection with Controlled Ablations
Zhou, H. (2026) · International Conference on Computer Vision, Image and Deep Learning (CVIDL) · doi:10.1109/cvidl70130.2026.11637922
Role of Image Steganography in Mitigating Deep Fakes
Soni, K., & Acharya, A. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-35173-9_7
Noman, A. A., Afiq, A. A., Kabir, M. H., Ahmad, Jaki, H., & Hasan, M. N. (2026) · Discover Computing · doi:10.1007/s10791-026-10477-3
Hanna, H. W., & Al-Orfali, A. K. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-39720-1_12
An overview of Challenges in Deepfake technology-detection and Mitigation
Shetty, A., & Hariharasitaraman, S. (2026) · International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC) · doi:10.1109/assic70037.2026.11716950
Metadata
- Authors
- Naitali, A., Ridouani, M., Salahdine, F., & Kaabouch, N.
- Affiliations
- University of Hassan II Casablanca (MA)
- University of North Carolina at Charlotte (US)
- University of North Dakota (US)
- Corresponding author
- Naitali, Amal
- Kaabouch, Naima
- Venue
- Computers
- Publisher
- MDPI AG
- Published
- 2023-10-23
- Volume
- 12
- Issue
- 10
- Pages
- 216
- ISSN
- 2073-431X (ISSN-L)
- OpenAlex
- W4387874311
- Cited by
- 117
- References
- 114
- Citations by year
- 2026: 28 · 2025: 56 · 2024: 33
- FWCI
- 10.62
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Computers (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- 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 › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Keywords
- deepfakes, deepfake detection, deepfake generation, deepfake datasets, misinformation, political manipulation, propaganda, reputational damage, fraud, 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.
A language model drew the claims from the paper on 2026-10-07, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-07 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (qwen3.8-omni-flash).
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.