Deepfake attribution: On the source identification of artificially generated images
The DOI matches its Crossref record; 34 of the 34 references it cites were found in a registry or an index.
Abstract
Synthetic media or "deepfakes" are making great advances in visual quality, diversity, and verisimilitude, empowered by large‐scale publicly accessible datasets and rapid technical progress in deep generative modeling. Heralding a paradigm shift in how online content is trusted, researchers in digital image forensics have responded with different proposals to reliably detect AI‐generated images in the wild. However, binary classification of image authenticity is insufficient to regulate the ethical usage of deepfake technology as new applications are developed. This article provides an overview of the major innovations in synthetic forgery detection as of 2020, while highlighting the recent shift in research towards ways to attribute AI‐generated images to their generative sources with evidence. We define the various categories of deepfakes in existence, the subtle processing traces and fingerprints that distinguish AI‐generated images from reality and each other, and the different degrees of attribution possible with current understanding of generative algorithms. Additionally, we describe the limitations of synthetic image recognition methods in practice, the counter‐forensic attacks devised to exploit these limitations, and directions for new research to assure the long‐term relevance of deepfake forensics. Reliable, explainable, and generalizable attribution methods would hold malicious users accountable for AI‐enabled disinformation, grant plausible deniability to appropriate users, and facilitate intellectual property protection of deepfake technology. This article is categorized under: Commercial, Legal, and Ethical Issues > Security and Privacy Algorithmic Development > Multimedia
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
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
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
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
Large Scale GAN Training for High Fidelity Natural Image Synthesis
Brock, A., Donahue, J., & Simonyan, K. (2018) · arXiv · doi:10.48550/arxiv.1809.11096 · Cited by 3,717
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 6×
“However, the success of data-driven spatial domain detectors (see Rössler et al., 2019) contradicts the implication that signal-level artifacts are completely absent in deepfake videos.”
BackgroundMethodInfluentialTorralba, A., & Efros, A. A. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995347 · Cited by 2,440 · cited 1×
“…approaches, which only consider a specific generative algorithm, are only effective on images created using that specific algorithm and that belong to the same ontological domain (e.g., LSUN category) as the training dataset due to dataset bias (Torralba & Efros, 2011; Wang, Wang, et al., 2020).”
BackgroundVoxCeleb2: Deep Speaker Recognition
Chung, J. S., Nagrani, A., & Zisserman, A. (2018) · Interspeech 2018 · doi:10.21437/interspeech.2018-1929 · Cited by 2,256
MesoNet: 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
Face2Face: 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
StarGAN v2: Diverse Image Synthesis for Multiple Domains
Choi, Y., Uh, Y., Yoo, J., & Ha, J.-W. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00821 · Cited by 1,663
Deepfakes 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
CNN-Generated Images Are Surprisingly Easy to Spot… for Now
Wang, S.-Y., Wang, O., Zhang, R., Owens, A., & Efros, A. A. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00872 · Cited by 1,210
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
The Emergence of Deepfake Technology: A Review
Westerlund, M. (2019) · Technology Innovation Management Review · doi:10.22215/timreview/1282 · Cited by 1,138
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
Deep Fakes: A Looming Challenge for Privacy, Democracy, and National Security
Chesney, R., & Citron, D. K. (2018) · SSRN Electronic Journal · doi:10.2139/ssrn.3213954 · Cited by 880 · cited 1×
“However, their potential to be used in committing cybercrime, inciting social unrest, and subverting political systems is alarming researchers and lawmakers alike (Chesney & Citron, 2018; Westerlund, 2019).”
BackgroundAttGAN: Facial attribute editing by only changing what you want
He, Z., Zuo, W., Kan, M., Shan, S., & Chen, X. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2916751 · Cited by 833 · cited 3×
“Attribute manipulation examples are made with AttGAN and StarGAN v2 (Choi et al., 2020; He et al., 2019), using the CelebA and CelebA-HQ datasets, respectively (Karras et al., 2018; Liu et al., 2015) for identity manipulation, this was how the term “ deepfake ” originated when referring to AI-manipulated videos of cel…”
MethodExploiting Visual Artifacts to Expose Deepfakes and Face Manipulations
Matern, F., Riess, C., & Stamminger, M. (2019) · 2019 IEEE Winter Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw.2019.00020 · Cited by 824
Few-Shot Adversarial Learning of Realistic Neural Talking Head Models
Zakharov, E., Shysheya, A., Burkov, E., & Lempitsky, V. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00955 · Cited by 687
First Order Motion Model for Image Animation
Siarohin, A., Lathuilière, S., Tulyakov, S., Ricci, E., & Sebe, N. (2020) · arXiv · doi:10.48550/arxiv.2003.00196 · Cited by 585 · cited 2×
“Recently, re-enactment generators capable of seamlessly animating static images have emerged (Siarohin et al., 2019; Zakharov et al., 2019), eliminating the requirement for large quantities of relevant source footage that previously constrained the proliferation of high-quality deepfakes among casual Internet users.”
BackgroundDetecting and Simulating Artifacts in GAN Fake Images
Zhang, X., Karaman, S., & Chang, S.-F. (2019) · 2019 IEEE International Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs47025.2019.9035107 · Cited by 567 · cited 11×
“In 2016 when GAN models were still restricted to low-resolution images, Odena et al. (2016) proved the existence of “ checkerboard artifacts ” in all images upsampled by ConvNets.”
BackgroundMethodInfluentialRecurrent convolutional strategies for face manipulation detection in videos
Sabir, E., Cheng, J., Jaiswal, A., AbdAlmageed, W., Masi, I., & Natarajan, P. (2019) · arXiv · doi:10.48550/arxiv.1905.00582 · Cited by 443 · cited 1×
“Classification algorithms for detecting deepfake videos exploit the frame-by-frame synthesis process of such videos that typically fail to enforce temporally coherent relationships between feature representations in consecutive frames (Amerini et al., 2019; Sabir et al., 2019).”
BackgroundDeepfake 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×
“Classification algorithms for detecting deepfake videos exploit the frame-by-frame synthesis process of such videos that typically fail to enforce temporally coherent relationships between feature representations in consecutive frames (Amerini et al., 2019; Sabir et al., 2019).”
BackgroundDetection of GAN-Generated Fake Images over Social Networks
Marra, F., Gragnaniello, D., Cozzolino, D., & Verdoliva, L. (2018) · 2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR) · doi:10.1109/mipr.2018.00084 · Cited by 399 · cited 4×
“…testing conditions, and forces the classifiers to learn mesoscopic artifacts and patterns more likely to survive laundering without compromising classification performance (Frank et al., 2020; Marra et al., 2018; Nataraj et al., 2019; Wang, Wang, et al., 2020; Yu et al., 2019; Zhang et al., 2019).”
BackgroundInfluentialLeveraging Frequency Analysis for Deep Fake Image Recognition
Frank, J., Eisenhofer, T., Schönherr, L., Fischer, A., Kolossa, D., & Holz, T. (2020) · arXiv · doi:10.48550/arxiv.2003.08685 · Cited by 390 · cited 13×
“Due to the lack of a standard benchmark for GAN image attribution, they proposed a dataset v also utilized by (Frank et al., 2020): either CelebA (human portraits) or LSUN bedrooms as the real image source, along with four GAN architectures for full image synthesis (ProGAN, SN-GAN (Miyato et al.,…”
BackgroundMethodInfluentialDo GANs leave artificial fingerprints?
Marra, F., Gragnaniello, D., Verdoliva, L., & Poggi, G. (2019) · 2019 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR) · doi:10.1109/mipr.2019.00103 · Cited by 361
Detecting GAN generated Fake Images using Co-occurrence Matrices
Nataraj, L., Mohammed, T. M., Manjunath, B. S., Chandrasekaran, S., Flenner, A., Bappy, J. H., & Roy-Chowdhury, A. K. (2019) · Electronic Imaging · doi:10.2352/issn.2470-1173.2019.5.mwsf-532 · Cited by 331
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
Deepfake Detection: Current Challenges and Next Steps
Lyu, S. (2020) · 2020 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) · doi:10.1109/icmew46912.2020.9105991 · Cited by 234
On the Generalization of GAN Image Forensics
Xuan, X., Peng, B., Wang, W., & Dong, J. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-31456-9_15 · Cited by 184
Evading Deepfake-Image Detectors with White- and Black-Box Attacks
Carlini, N., & Farid, H. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00337 · Cited by 170
Vulnerability assessment and detection of Deepfake videos
Korshunov, P., & Marcel, S. (2019) · 2019 International Conference on Biometrics (ICB) · doi:10.1109/icb45273.2019.8987375 · Cited by 162 · cited 1×
“There are no barriers preventing the use of AI-generated images such as face swaps and fully synthetic portraits as inputs to FR systems, though Korshunov and Marcel (2019) have shown that these systems are unable to discern identity manipulation attacks, with severe security implications.”
BackgroundGANprintR: Improved Fakes and Evaluation of the State of the Art in Face Manipulation Detection
Neves, J. C., Tolosana, R., Vera-Rodriguez, R., Lopes, V., Proenca, H., & Fierrez, J. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.3007250 · Cited by 12
Cited by
Sai, S., Yashvardhan, U., Chamola, V., & Sikdar, B. (2024) · IEEE Access · doi:10.1109/access.2024.3385107 · Cited by 125
Typology of Risks of Generative Text-to-Image Models
Bird, C., Ungless, E., & Kasirzadeh, A. (2023) · Proceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3600211.3604722 · Cited by 121
Deepfake Media Forensics: Status and Future Challenges
Amerini, I., Barni, M., Battiato, S., Bestagini, P., Boato, G., Bruni, V., Caldelli, R., De Natale, F., De Nicola, R., Guarnera, L., et al. (2025) · Journal of Imaging · doi:10.3390/jimaging11030073 · Cited by 113
Metadata
- Authors
- Khoo, B., Phan, R. C. ‐., & Lim, C.
- Venue
- WIREs Data Mining and Knowledge Discovery
- Publisher
- Wiley
- Published
- 2021-12-03
- Volume
- 12
- Issue
- 3
- ISSN
- 1942-4787 (ISSN-L)
- 1942-4795
- OpenAlex
- W4200053273
- Cited by
- 54
- References
- 34
- FWCI
- 1.94
- Type
- journal article
- Language
- en
- Open access
- closed
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.