Deepfake Detection: A Comprehensive Survey from the Reliability Perspective
Open accessAbstract
The mushroomed Deepfake synthetic materials circulated on the internet have raised a profound social impact on politicians, celebrities, and individuals worldwide. In this survey, we provide a thorough review of the existing Deepfake detection studies from the reliability perspective. We identify three reliability-oriented research challenges in the current Deepfake detection domain: transferability, interpretability, and robustness. Moreover, while solutions have been frequently addressed regarding the three challenges, the general reliability of a detection model has been barely considered, leading to the lack of reliable evidence in real-life usages and even for prosecutions on Deepfake-related cases in court. We, therefore, introduce a model reliability study metric using statistical random sampling knowledge and the publicly available benchmark datasets to review the reliability of the existing detection models on arbitrary Deepfake candidate suspects. Case studies are further executed to justify the real-life Deepfake cases including different groups of victims with the help of the reliably qualified detection models as reviewed in this survey. Reviews and experiments on the existing approaches provide informative discussions and future research directions for Deepfake detection.
Integrity signals
Registry
Cites
Statistics
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?
Explainable AI provides a diagnostic lens that reveals whether a model relies on generalizable manipulation traces or overfits to superficial, generator-specific cues.
“Explainable AI provides a diagnostic lens that reveals whether a model relies on fundamental generalizable manipulation traces, such as blending boundaries or frequency inconsistencies, or overfits to superficial, generator-specific cues [6].”
From From Black Boxes to Glass Boxes: Explainable AI for Trustworthy Deepfake Forensics (2025) · cites this paper as [6]
Standard metrics for deepfake detection (Accuracy, AUC, EER) measure classification accuracy but do not address the interpretability of a model's decisions.
“Standard metrics for evaluating deepfake detection performance typically include Accuracy, Area Under the Curve (AUC), and Equal Error Rate (EER) [6]. While these metrics effectively measure a model's classification accuracy, they do not address the interpretability of its decisions.”
From From Black Boxes to Glass Boxes: Explainable AI for Trustworthy Deepfake Forensics (2025) · cites this paper as [6]
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 · see citing works
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 · see citing works
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 · see citing works
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
Deng, J., Guo, J., Xue, N., & Zafeiriou, S. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00482 · Cited by 7,781 · see citing works
Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions
Wang, W., Xie, E., Li, X., Fan, D.-P., Song, K., Liang, D., Lu, T., Luo, P., & Shao, L. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00061 · Cited by 5,259 · cited 1× · see citing works
“1) of the current Deepfake detection research domain can be summarized regarding the reliability goal, namely, transferability, interpretability, and robustness.”
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 · see citing works
Rich Models for Steganalysis of Digital Images
Fridrich, J., & Kodovsky, J. (2012) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2012.2190402 · Cited by 2,144 · see citing works
Celeb-DF: A Large-Scale Challenging Dataset for DeepFake Forensics
Li, Y., Yang, X., Sun, P., Qi, H., & Lyu, S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00327 · Cited by 1,846 · cited 3× · see citing works
“…directly upon videos, for the frame-level detectors, since the detection results are evaluated based on all selected frames, to avoid potential biases toward particular videos, it is meaningful to keep the amount of extracted faces from each video equivalent during model training and testing.”
InfluentialDeepfakes and beyond: A Survey of face manipulation and fake detection
Tolosana, R., Vera-Rodriguez, R., Fierrez, J., Morales, A., & Ortega-Garcia, J. (2020) · Information Fusion · doi:10.1016/j.inffus.2020.06.014 · Cited by 1,237 · see citing works
Multi-attentional Deepfake Detection
Zhao, H., Wei, T., Zhou, W., Zhang, W., Chen, D., & Yu, N. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00222 · Cited by 1,019 · cited 6× · see citing works
“Then the models are further discussed regarding the reliability following Algorithm 1 along with case studies on real-life Deepfake materials.”
InfluentialThe Creation and Detection of Deepfakes: A Survey
Mirsky, Y., & Lee, W. (2020) · arXiv · doi:10.48550/arxiv.2004.11138 · Cited by 863
Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domain
Liu, H., Li, X., Zhou, W., Chen, Y., He, Y., Xue, H., Zhang, W., & Yu, N. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00083 · Cited by 600 · see citing works
DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection
Jiang, L., Li, R., Wu, W., Qian, C., & Loy, C. C. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00296 · Cited by 599 · see citing works
Loyola-Gonzalez, O. (2019) · IEEE Access · doi:10.1109/access.2019.2949286 · Cited by 559 · see citing works
Detecting Deepfakes with Self-Blended Images
Shiohara, K., & Yamasaki, T. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01816 · Cited by 503 · see citing works
DeepFakes: a New Threat to Face Recognition? Assessment and Detection
Korshunov, P., & Marcel, S. (2018) · arXiv · doi:10.48550/arxiv.1812.08685 · Cited by 497 · see citing works
End-to-End Reconstruction-Classification Learning for Face Forgery Detection
Cao, J., Ma, C., Yao, T., Chen, S., Ding, S., & Yang, X. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00408 · Cited by 428 · see citing works
The deepfake detection challenge (dfdc) dataset
Dolhansky, B., Bitton, J., Pflaum, B., Lu, J., Howes, R., Wang, M., & Ferrer, C. C. (2020) · arXiv · doi:10.48550/arxiv.2006.07397 · Cited by 427 · see citing works
Deepfake Video Detection through Optical Flow Based CNN
Amerini, I., Galteri, L., Caldelli, R., & Del Bimbo, A. (2019) · 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) · doi:10.1109/iccvw.2019.00152 · Cited by 424 · cited 2× · see citing works
“Moreover, heatmaps of the real faces are displayed in like manners, which are indistinguishable from that of the fake ones.”
The Deepfake Detection Challenge (DFDC) Preview Dataset
Dolhansky, B., Howes, R., Pflaum, B., Baram, N., & Ferrer, C. C. (2019) · arXiv · doi:10.48550/arxiv.1910.08854 · Cited by 413 · see citing works
AI-synthesized faces are indistinguishable from real faces and more trustworthy
Nightingale, S. J., & Farid, H. (2022) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2120481119 · Cited by 397 · see citing works
Learning Self-Consistency for Deepfake Detection
Zhao, T., Xu, X., Xu, M., Ding, H., Xiong, Y., & Xia, W. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01475 · Cited by 383 · see citing works
Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection
Chen, L., Zhang, Y., Song, Y., Liu, L., & Wang, J. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01815 · Cited by 307 · see citing works
Deep fake image detection based on pairwise learning
Hsu, C.-C., Zhuang, Y.-X., & Lee, C.-Y. (2020) · Applied Sciences · doi:10.3390/app10010370 · Cited by 304 · see citing works
Detecting Deep-Fake Videos from Appearance and Behavior
Agarwal, S., Farid, H., El-Gaaly, T., & Lim, S.-N. (2020) · 2020 IEEE International Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs49906.2020.9360904 · Cited by 242 · cited 1× · see citing works
“The most recent KoDF [95] dataset is so far the largest Deepfake benchmark dataset that is publicly available with reasonable diversity and contains synthetic videos at high resolutions.”
DeepRhythm: Exposing DeepFakes with Attentional Visual Heartbeat Rhythms
Qi, H., Guo, Q., Juefei-Xu, F., Xie, X., Ma, L., Feng, W., Liu, Y., & Zhao, J. (2020) · Proceedings of the 28th ACM International Conference on Multimedia · doi:10.1145/3394171.3413707 · Cited by 220 · see citing works
Dual Contrastive Learning for General Face Forgery Detection
Sun, K., Yao, T., Chen, S., Ding, S., Li, J., & Ji, R. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i2.20130 · Cited by 209 · see citing works
ExprGAN: Facial Expression Editing With Controllable Expression Intensity
Ding, H., Sricharan, K., & Chellappa, R. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.12277 · Cited by 207 · see citing works
Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection
Haliassos, A., Mira, R., Petridis, S., & Pantic, M. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01453 · Cited by 180 · see citing works
Fake face detection via adaptive manipulation traces extraction network
Guo, Z., Yang, G., Chen, J., & Sun, X. (2021) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2021.103170 · Cited by 165 · see citing works
HifiFace: 3D Shape and Semantic Prior Guided High Fidelity Face Swapping
Wang, Y., Chen, X., Zhu, J., Chu, W., Tai, Y., Wang, C., Li, J., Wu, Y., Huang, F., & Ji, R. (2021) · Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2021/157 · Cited by 138 · see citing works
Self-citationFrePGAN: Robust Deepfake Detection Using Frequency-Level Perturbations
Jeong, Y., Kim, D., Ro, Y., & Choi, J. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i1.19990 · Cited by 137 · see citing works
Snis: a signal noise separation-based network for post-processed image forgery detection
Chen, J., Liao, X., Wang, W., Qian, Z., Qin, Z., & Wang, Y. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3204753 · Cited by 129 · see citing works
Self-citationDeep convolutional pooling transformer for deepfake detection
Wang, T., Cheng, H., Chow, K. P., & Nie, L. (2023) · ACM Transactions on Multimedia Computing, Communications, and Applications · doi:10.1145/3588574 · Cited by 111 · see citing works
Self-citationNoise Based Deepfake Detection via Multi-Head Relative-Interaction
Wang, T., & Chow, K. P. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i12.26701 · Cited by 93 · cited 1× · see citing works
“Therefore, the PRNU noise pattern can be a useful instrument for source device identification tasks, but it may not be a meaningful forensic noise tracing tool to satisfy the purpose of the Deepfake detection task with respect to the interpretability goal.”
Self-citationBlind PRNU-Based Image Clustering for Source Identification
Marra, F., Poggi, G., Sansone, C., & Verdoliva, L. (2017) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2017.2701335 · Cited by 84 · cited 1× · see citing works
“In a nutshell, the interpretability challenge is to answer the following questions regarding a Deepfake suspect in order to be reliable: • Why is the content classified as fake?”
Fdftnet: facing off fake images using fake detection fine-tuning network
Jeon, H., Bang, Y., & Woo, S. S. (2020) · IFIP Advances in Information and Communication Technology · doi:10.1007/978-3-030-58201-2_28 · Cited by 65 · see citing works
Supervised Contrastive Learning for Generalizable and Explainable DeepFakes Detection
Xu, Y., Raja, K., & Pedersen, M. (2022) · 2022 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw54805.2022.00044 · Cited by 62 · cited 1× · see citing works
“For the Deepfake detection task, while achieving promising detection performance statistically for in-and cross-dataset evaluations, the interpretability issue is still maintained to be fully resolved at the current stage.”
Exploring Disentangled Content Information for Face Forgery Detection
Liang, J., Shi, H., & Deng, W. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-19781-9_8 · Cited by 58 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Qureshi, S. M., Saeed, A., Almotiri, S. H., Ahmad, F., & Al Ghamdi, M. A. (2024) · PeerJ Computer Science · doi:10.7717/peerj-cs.2037 · Cited by 71 · see citing works
From Black Boxes to Glass Boxes: Explainable AI for Trustworthy Deepfake Forensics
Qian, H., Xia, L., Ge, R., Fan, Y., Wang, Q., & Jing, Z. (2025) · Cryptography · doi:10.3390/cryptography9040061 · Cited by 10 · see citing works
“Explainable AI provides a diagnostic lens that reveals whether a model relies on fundamental generalizable manipulation traces, such as blending boundaries or frequency inconsistencies, or overfits to superficial, generator-specific cues [6].”
- Authors
- Wang, T., Liao, X., Chow, K. P., Lin, X., & Wang, Y.
- Affiliations
- University of Hong Kong (HK)
- Hunan University (CN)
- University of Guelph (CA)
- Qilu University of Technology (CN)
- Venue
- ACM Computing Surveys
- Published
- 2024-11-11
- Volume
- 57
- Issue
- 3
- Pages
- 1-35
- ISSN
- 0360-0300 (ISSN-L)
- 1557-7341
- OpenAlex
- W4403221680
- Cited by
- 107
- References
- 39
- Citations by year
- 2026: 53 · 2025: 48 · 2024: 3 · 2023: 1 · 2017: 2
- FWCI
- 14.56
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- ACM Computing Surveys (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China (U22A2030)
- National Key R&D Program of China (2022YFB3103500)
- Hunan Provincial Funds for Distinguished Young Scholars (2024JJ2025)
- 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
- deepfake detection, model reliability, transferability, interpretability, robustness, benchmark dataset, 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
