Artifacts-Disentangled Adversarial Learning for Deepfake Detection
The DOI matches its Crossref record; 23 of the 23 references it cites were found in a registry or an index.
Abstract
Due to the development of facial manipulation technologies, the generated deepfake videos cause a severe trust crisis in society. Existing methods prove that effective extraction of the artifacts introduced during the forgery process is essential for deepfake detection. However, since the features extracted by supervised binary classification contain a lot of artifact-irrelevant information, existing algorithms suffer severe performance degradation in the case of the mismatch between training and testing datasets. To overcome this issue, we propose an Artifacts-Disentangled Adversarial Learning (ADAL) framework to achieve accurate deepfake detection by disentangling the artifacts from irrelevant information. Furthermore, the proposed algorithm provides visual evidence by effectively estimating artifacts. Specifically, Multi-scale Feature Separator (MFS) in the disentanglement generator is designed to precisely transmit the artifact features and optimize the connection between the encoder and decoder. In addition, we design an Artifacts Cycle Consistency Loss (ACCL) which uses the disentangled artifacts to construct new samples and enables pixel-level supervised training for the generator to estimate more accurate artifacts. The symmetric discriminators are paralleled to differentiate the constructed samples from the original images in both fake and real domains, making the adversarial training process more stable. Extensive experiments on existing benchmarks demonstrate that the proposed method outperforms the state-of-the-art approaches.
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.
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
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
Tan, M., & Le, Q. V. (2019) · arXiv · doi:10.48550/arxiv.1905.11946 · Cited by 17,072 · cited 5×
“be seen that supervised binary classification methods (XceptionNet [11], EfficientNet [12]) show a drastic degradation in performance.”
MethodInfluentialJoint 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
FaceForensics++: Learning to Detect Manipulated Facial Images
Rossler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., & Niessner, M. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00009 · Cited by 3,314 · cited 9×
“be seen that supervised binary classification methods (XceptionNet [11], EfficientNet [12]) show a drastic degradation in performance.”
BackgroundMethodInfluentialMesoNet: a Compact Facial Video Forgery Detection Network
Afchar, D., Nozick, V., Yamagishi, J., & Echizen, I. (2018) · 2018 IEEE International Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs.2018.8630761 · Cited by 1,872
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 1×
“Celeb-DFv2 [45] is generally the most challenging case for the current detection methods because it contains many different subjects (e.g., age, skin color, gender) and a high degree of deceptiveness; There are 590 real videos and 5639 fake videos.”
BackgroundFace2Face: Real-Time Face Capture and Reenactment of RGB Videos
Thies, J., Zollhofer, M., Stamminger, M., Theobalt, C., & Niessner, M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.262 · Cited by 1,747
Face X-Ray for More General Face Forgery Detection
Li, L., Bao, J., Zhang, T., Yang, H., Chen, D., Wen, F., & Guo, B. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00505 · Cited by 1,211
Exposing Deep Fakes Using Inconsistent Head Poses
Yang, X., Li, Y., & Lyu, S. (2019) · ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2019.8683164 · Cited by 1,196
In Ictu Oculi: Exposing AI Created Fake Videos by Detecting Eye Blinking
Li, Y., Chang, M.-C., & Lyu, S. (2018) · 2018 IEEE International Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs.2018.8630787 · Cited by 1,089
Thinking in Frequency: Face Forgery Detection by Mining Frequency-Aware Clues
Qian, Y., Yin, G., Sheng, L., Chen, Z., & Shao, J. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58610-2_6 · Cited by 1,058
Research works printed but not linked: 25
- 2020, DeepFakes Github
- 2020, Faceswap Github
- 10.1109/ICCVW.2019.00213 · DOI · Paper page
- Agarwal, Protecting world leaders against deep fakes, 38
- 10.1109/AVSS.2018.8639163 · DOI · Paper page
- 10.1109/TIFS.2022.3146781 · DOI · Paper page
- 10.1109/CVPR.2017.195 · DOI · Paper page
- 10.1109/TCSVT.2015.2473436 · DOI
- 10.1109/TCSVT.2020.2993004 · DOI · Paper page
- 10.1109/TCSVT.2018.2804768 · DOI · Paper page
- 10.1109/TCSVT.2018.2852799 · DOI
- 10.1109/TCSVT.2016.2593612 · DOI
- 10.1109/TCSVT.2021.3074259 · DOI · Paper page
- 10.1109/TPAMI.2018.2868350 · DOI · Paper page
- 10.1109/TCSVT.2020.3024201 · DOI
- 10.1109/CVPR.2018.00547 · DOI · Paper page
- 10.1109/CVPR.2019.00484 · DOI · Paper page
- Denton, Unsupervised learning of disentangled representations from video, 4414
- 10.1007/978-3-030-58523-5_24 · DOI
- 10.1109/ICCVW.2017.190 · DOI · Paper page
- 10.1109/CVPR.2017.632 · DOI · Paper page
- 10.1145/3306346.3323035 · DOI · Paper page
- Dufour, 2019, Contributing data to deepfake detection research
- Dolhansky, 2020, The DeepFake detection challenge dataset, arXiv:2006.07397 · arXiv
- der Maaten, 2008, Visualizing data using t-SNE, J. Mach. Learn. Res., 9, 2579
Cited by
Good models borrow, great models steal: intellectual property rights and generative AI
Chesterman, S. (2025) · Policy and Society · doi:10.1093/polsoc/puae006 · Cited by 156
A Review of Deepfake Techniques: Architecture, Detection and Datasets
Edwards, P., Nebel, J.-C., Greenhill, D., & Liang, X. (2024) · IEEE Access · doi:10.1109/access.2024.3477257 · Cited by 50
Exploring autonomous methods for deepfake detection: A detailed survey on techniques and evaluation
Sunil, R., Mer, P., Diwan, A., Mahadeva, R., & Sharma, A. (2025) · Heliyon · doi:10.1016/j.heliyon.2025.e42273 · Cited by 54
Forgery-Aware Adaptive Learning With Vision Transformer for Generalized Face Forgery Detection
Luo, A., Cai, R., Kong, C., Ju, Y., Kang, X., Huang, J., & Kot, A. C. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3522091 · Cited by 41
She, H., Hu, Y., Liu, B., Li, J., & Li, C.-T. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3451356 · Cited by 24
“Following the evaluation protocol in [63], [64], and [65], we conduct cross-dataset between different subsets in the FF ++ (C23).”
Method
Metadata
- Authors
- Li, X., Ni, R., Yang, P., Fu, Z., & Zhao, Y.
- Venue
- IEEE Transactions on Circuits and Systems for Video Technology
- Published
- 2023-04
- Volume
- 33
- Issue
- 4
- Pages
- 1658-1670
- ISSN
- 1051-8215 (ISSN-L)
- 1558-2205
- OpenAlex
- W4312782746
- Cited by
- 93
- References
- 23
- FWCI
- 6.15
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Funders
- National Key Research and Development Program of China (2021ZD0112100)
- National Natural Science Foundation of China (U1936212, 62120106009)
- Beijing Natural Science Foundation (4222014)
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: Artifacts-Disentangled Adversarial Learning for Deepfake Detection. https://app.cochat.ai/papers/10.1109/tcsvt.2022.3217950
- The paper
- Li, X., Ni, R., Yang, P., Fu, Z., & Zhao, Y. (2023). Artifacts-Disentangled Adversarial Learning for Deepfake Detection. IEEE Transactions on Circuits and Systems for Video Technology. https://doi.org/10.1109/tcsvt.2022.3217950
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.