The DOI matches its Crossref record; 21 of the 21 references it cites were found in a registry or an index.
Detecting and Simulating Artifacts in GAN Fake Images
Open accessAbstract
To detect GAN generated images, conventional supervised machine learning algorithms require collecting a large number of real images as well as fake images generated by the targeted GAN model. However, the specific model used by the attacker is often unavailable. To address this, we propose a GAN simulator, AutoGAN, which can simulate the artifacts produced by the common pipeline shared by several popular GAN models. Additionally, we identify a unique artifact caused by the up-sampling component included in the common GAN pipelines. We show theoretically such artifacts are manifested as replications of spectra in the frequency domain and thus propose a classifier model based on the spectrum input, rather than the pixel input. By using the simulated images to train a spectrum based classifier, even without seeing the fake images produced by the targeted GAN model during training, our approach achieves state-of-the-art performances on detecting fake images generated by popular GAN models such as CycleGAN.
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
“Figure 7 represents the potentials of employing the frequency artifacts for detecting DeepFakes, where the GAN-based manipulation introduces invisible artifacts in the frequency domain.”
From Countering Malicious DeepFakes: Survey, Battleground, and Horizon (2022) · cites this paper as Zhang et al. 2019
In the citing paper
“Due to limited data, network structure,8 and optimization algorithms,6 the GANs can hardly fit the distribution of real data.”
From Deepfakes: A new threat to image fabrication in scientific publications? (2022) · cites this paper as [8]
In the citing paper
“The most well-known artifact is the checkerboard effect due to the image upsampling operation in GAN.8”
From Deepfakes: A new threat to image fabrication in scientific publications? (2022) · cites this paper as [8]
Citations
Cites
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
Image-to-Image Translation with Conditional Adversarial Networks
Isola, P., Zhu, J.-Y., Zhou, T., & Efros, A. A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.632 · Cited by 22,930 · cited 1×
“image that is constrained by the layout of the sketch [11], [6], [10].”
BackgroundLabaca-Castro, R. (2023) · Springer eBooks · doi:10.1007/978-3-658-40442-0_9 · Cited by 21,119
GAN（Generative Adversarial Nets）
淳司, 柴. (2017) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.29.5_177_2 · Cited by 20,507
Unsupervised representation learning with deep convolutional generative adversarial networks
Radford, A., Metz, L., & Chintala, S. (2015) · arXiv · doi:10.48550/arxiv.1511.06434 · Cited by 12,235 · cited 1×
“a deconvolution) [19], [6], [7] and nearest neighbor interpolation [9], [10].”
BackgroundA 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 · cited 2×
“In image generation, GAN [1] can be applied in the following scenarios: 1) taking noise as input to produce an image [9], [2], [3]; 2) taking an image from one semantic category (such as horse) as input to produce an image of another semantic category (such as zebra) [6], [7], [10]; 3) taking a sketch or a pixel level…”
BackgroundMethodProgressive Growing of GANs for Improved Quality, Stability, and Variation
Karras, T., Aila, T., Laine, S., & Lehtinen, J. (2017) · arXiv · doi:10.48550/arxiv.1710.10196 · Cited by 4,727 · cited 4×
“) [6] and nearest neighbor interpolation (NN) [9].”
BackgroundMethodInfluentialStarGAN: 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 · cited 2×
“In image generation, GAN [1] can be applied in the following scenarios: 1) taking noise as input to produce an image [9], [2], [3]; 2) taking an image from one semantic category (such as horse) as input to produce an image of another semantic category (such as zebra) [6], [7], [10]; 3) taking a sketch or a pixel level…”
BackgroundMethodSemantic Image Synthesis With Spatially-Adaptive Normalization
Park, T., Liu, M.-Y., Wang, T.-C., & Zhu, J.-Y. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00244 · Cited by 2,974 · cited 5×
“However, all classifiers fail on GauGAN images, since the generator structure of GauGAN (5 nearest neighbor up-samplers) is drastically different from the CycleGAN structure.”
BackgroundMethodInfluential
Cited by
Sorted by citations
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
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
Media Forensics and DeepFakes: An Overview
Verdoliva, L. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.3002101 · Cited by 979
“In [174], instead, a GAN simulator is proposed to reproduce common GAN-image artifacts, which manifest as spectral peaks in the Fourier domain.”
BackgroundThinking 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
Metadata
- Authors
- Zhang, X., Karaman, S., & Chang, S.-F.
- Affiliations
- Columbia University (US)
- Venue
- 2019 IEEE International Workshop on Information Forensics and Security (WIFS)
- Publisher
- IEEE
- Published
- 2019-12
- Pages
- 1-6
- ISSN
- 2157-4774 (ISSN-L)
- OpenAlex
- W3012472557
- Cited by
- 567
- References
- 21
- Citations by year
- 2026: 60 · 2025: 113 · 2024: 89 · 2023: 100 · 2022: 84 · 2021: 81 · 2020: 39
- FWCI
- 16.52
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE International Workshop on Information Forensics and Security (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- 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 › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Keywords
- GAN-generated image detection, CycleGAN, adversarial image generation
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
