Artifact: A Large-Scale Dataset With Artificial And Factual Images For Generalizable And Robust Synthetic Image Detection
The DOI matches its Crossref record; 27 of the 27 references it cites were found in a registry or an index.
Abstract
Synthetic image generation has opened up new opportunities but has also created threats in regard to privacy, authenticity, and security. Detecting fake images is of paramount importance to prevent illegal activities, and previous research has shown that generative models leave unique patterns in their synthetic images that can be exploited to detect them. However, the fundamental problem of generalization remains, as even state-of-the-art detectors encounter difficulty when facing generators never seen during training. To assess the generalizability and robustness of synthetic image detectors in the face of real-world impairments, this paper presents a large-scale dataset1named ArtiFact, comprising diverse generators, object categories, and real-world challenges. Moreover, the proposed multi-class classification scheme, combined with a filter stride reduction strategy addresses social platform impairments and effectively detects synthetic images from both seen and unseen generators. The proposed solution significantly outperforms other top teams by 8.34% on Test 1, 1.26% on Test 2, and 15.08% on Test 3 in the IEEE VIP Cup challenge at ICIP 2022, as measured by the accuracy metric.
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
“The dataset contains over 2.4 million images, with 1.5 million synthetic images generated using 25 different methods, including GANs, diffusion models, and other generative techniques.”
From Deepfake Media Forensics: Status and Future Challenges (2025) · cites this paper as [34]
Citations
Cites
Scikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016 · cited 1×
“To evaluate the detector’s generalizability reliably, a four-fold hybrid cross-validation scheme is implemented with balanced accuracy which applies KFold [27] for real class and five seen fake classes where data from the same generators can appear in both the train and test sets as well as GroupKFold [27] for the uns…”
MethodLiu, Z., Mao, H., Wu, C.-Y., Feichtenhofer, C., Darrell, T., & Xie, S. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01167 · Cited by 8,494 · cited 2×
“To tackle this problem, a novel approach is put forth, which reduces the filter stride in the stem block of the ConvNeXt [26] backbone by 2 × as shown in Fig.”
MethodStarGAN: 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
Taming Transformers for High-Resolution Image Synthesis
Esser, P., Rombach, R., & Ommer, B. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01268 · Cited by 2,514
Taming Transformers for High-Resolution Image Synthesis
Esser, P., Rombach, R., & Ommer, B. (2020) · arXiv · doi:10.48550/arxiv.2012.09841 · Cited by 2,514
Free-Form Image Inpainting With Gated Convolution
Yu, J., Lin, Z., Yang, J., Shen, X., Lu, X., & Huang, T. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00457 · Cited by 1,928
Diffusion Models in Vision: A Survey
Croitoru, F.-A., Hondru, V., Ionescu, R. T., & Shah, M. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3261988 · Cited by 1,859 · cited 2×
“Additionally, to inject diversity in terms of generators, the proposed dataset synthesizes images from 25 distinct methods [7]–[9], [14]–[24].”
BackgroundPalette: Image-to-Image Diffusion Models
Saharia, C., Chan, W., Chang, H., Lee, C., Ho, J., Salimans, T., Fleet, D., & Norouzi, M. (2022) · Special Interest Group on Computer Graphics and Interactive Techniques Conference Proceedings · doi:10.1145/3528233.3530757 · Cited by 1,717 · cited 1×
“Additionally, to inject diversity in terms of generators, the proposed dataset synthesizes images from 25 distinct methods [7]–[9], [14]–[24].”
GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
Nichol, A., Dhariwal, P., Ramesh, A., Shyam, P., Mishkin, P., McGrew, B., Sutskever, I., & Chen, M. (2021) · arXiv · doi:10.48550/arxiv.2112.10741 · Cited by 1,357
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
Research works printed but not linked: 1
- Beniaguev, 2022, Synthetic faces high quality (sfhq) dataset
Cited by
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
“Artifact [34] is a dataset designed to evaluate the generalizability and robustness of synthetic image detectors.”
Security and Privacy on Generative Data in AIGC: A Survey
Wang, T., Zhang, Y., Qi, S., Zhao, R., Xia, Z., & Weng, J. (2024) · ACM Computing Surveys · doi:10.1145/3703626 · Cited by 155
“Therefore, the development of interpretable, trustworthy, and easy-to-handle detection tools will be able to attract more social attention and popularization, thus promoting the friendly usage of detection techniques for disadvantaged groups, including unskilled users and the elderly.”
Huang, Z., Hu, J., Li, X., He, Y., Zhao, X., Peng, B., Wu, B., Huang, X., & Cheng, G. (2025) · 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52734.2025.02685 · Cited by 62
“0[12] General Corel 2022 ✗ ✓ ✗ ArtiFact[55] General COCO,FFHQ,LSUN 2023 ✗ ✗ ✗ IMD2020[47] General Places2 2020 ✗ ✓ ✗ AIGCD[87] General LSUN,COCO,FFHQ 2023 ✗ ✗ ✗ GenImage[89] General”
Detecting Images Generated by Deep Diffusion Models using their Local Intrinsic Dimensionality
Lorenz, P., Durall, R., & Keuper, J. (2023) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw60793.2023.00051 · Cited by 81
“ArtiFact is a large-scale image dataset [6], which includes a diverse collection of real and synthetic images from multiple categories: human/human faces, animal/animal faces, places, vehicles, art, and many other real-life objects.”
BackgroundZhang, Y., Pang, Z., Huang, S., Wang, C., & Zhou, X. (2025) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-025-00154-8 · Cited by 47
Metadata
- Authors
- Rahman, M. A., Paul, B., Sarker, N. H., Hakim, Z. I. A., & Fattah, S. A.
- Affiliations
- Bangladesh University of Engineering and Technology (BD)
- Venue
- 2023 IEEE International Conference on Image Processing (ICIP)
- Publisher
- IEEE
- Published
- 2023-10-08
- Pages
- 2200-2204
- ISSN
- 1522-4880 (ISSN-L)
- OpenAlex
- W4386590429
- Cited by
- 34
- References
- 27
- Citations by year
- 2026: 7 · 2025: 15 · 2024: 11 · 2023: 1
- FWCI
- 3.64
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Proceedings - International Conference on Image Processing (publishedVersion)
- 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
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Steganography and Watermarking Techniques
- Keywords
- synthetic image detection, generative adversarial networks, fake image detection, multi-class classification
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: Artifact: A Large-Scale Dataset With Artificial And Factual Images For Generalizable And Robust Synthetic Image Detection. https://app.cochat.ai/papers/10.1109/icip49359.2023.10222083
- The paper
- Rahman, M. A., Paul, B., Sarker, N. H., Hakim, Z. I. A., & Fattah, S. A. (2023). Artifact: A Large-Scale Dataset With Artificial And Factual Images For Generalizable And Robust Synthetic Image Detection. 2023 IEEE International Conference on Image Processing (ICIP). https://doi.org/10.1109/icip49359.2023.10222083
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.