Can Forensic Detectors Identify GAN Generated Images?
The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
Abstract
Generative adversarial network (GAN) has shown its powerful capability in generating photorealistic images. Although the generated images can fool human eyes, it is not clear whether they can evade the detection of forensic detectors, which aim to identify the originality and authenticity of images. In this paper, we investigate how forensic detectors perform in differentiating between GAN generated images and real images. We consider two kinds of approaches, one is intrusive and the other is non-intrusive, based on whether the GAN architecture is needed for performing detection. We have conducted extensive experiments on a celebrity face image dataset to evaluate the effectiveness of different approaches. The results and analyses show that the intrusive approach can detect GAN generated images but with a relatively high false alarm rate. The non-intrusive approach with features extracted from a VGG network is very effective for detecting GAN generated images when the training data is sufficient, but it still faces challenge when the training data and testing data are mismatched.
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
Globally and locally consistent image completion
Iizuka, S., Simo-Serra, E., & Ishikawa, H. (2017) · ACM Transactions on Graphics · doi:10.1145/3072959.3073659 · Cited by 2,203 · cited 1×
“In recent years, generative models based on GAN [1] have attracted more and more attention in many applications, such as speech synthesis [2], image super-resolution [3], image translation [4], [5], and image inpainting [6].”
BackgroundEnergy-based Generative Adversarial Network
Zhao, J., Mathieu, M., & LeCun, Y. (2016) · arXiv · doi:10.48550/arxiv.1609.03126 · Cited by 912
Research works printed but not linked: 18
- arjovsky, 2017, Wasserstein GAN
- gulrajani, 2017, Improved training of Wasserstein GANs, Proc Conf Neural Information Processing Systems (NIPS), 5769
- karras, 2018, Progressive growing of GANs for improved quality, stability, and variation, Proc of the Int Conf on Learning Representations (ICLR)
- 10.1109/LSP.2014.2347419 · DOI
- salimans, 2016, Improved techniques for training GANs, Proc Conf Neural Information Processing Systems (NIPS), 2234
- simonyan, 2014, Very Deep Convolutional Networks for Large-scale Image Recognition
- 10.1109/ICCV.2015.425 · DOI · Paper page
- ioffe, 2015, Batch normalization: Accelerating deep network training by reducing internal covariate shift, Proc Int Conf Machine Learning (ICML), 448
- 10.1145/775047.775067 · DOI · Paper page
- 10.1109/CVPR.2016.308 · DOI · Paper page
- 10.1109/ICCV.2017.244 · DOI · Paper page
- 10.1109/CVPR.2017.19 · DOI · Paper page
- liu, 2017, Unsupervised image-to-image translation networks, Proc Conf Neural Information Processing Systems (NIPS), 700
- 10.1109/ICCV.2017.304 · DOI · Paper page
- radford, 2016, Unsupervised representation learning with deep convolutional generative adversarial networks, Proc of the Int Conf on Learning Representations (ICLR)
- van den oord, 2016, WaveNet A Generative Model for Raw Audio
- goodfellow, 2014, Generative adversarial nets, Proc Conf Neural Information Processing Systems (NIPS), 2672
- 10.1109/TIFS.2011.2175919 · DOI · Paper page
Cited by
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
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
Countering Malicious DeepFakes: Survey, Battleground, and Horizon
Juefei-Xu, F., Wang, R., Huang, Y., Guo, Q., Ma, L., & Liu, Y. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-022-01606-8 · Cited by 191
“The UADFV dataset (Li et al., 2018b) consists of 98 videos, with 49 real videos from YouTube and 49 synthesized videos, which are made using the FakeAPP (FaceApp, 2021).”
BackgroundMethodDeepfake generation and detection, a survey
Zhang, T. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11733-y · Cited by 176
Beyond Deepfake Images: Detecting AI-Generated Videos
Vahdati, D. S., Nguyen, T. D., Azizpour, A., & Stamm, M. C. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00443 · Cited by 37
Metadata
- Authors
- Li, H., Chen, H., Li, B., & Tan, S.
- Venue
- 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)
- Publisher
- IEEE
- Published
- 2018-11
- Pages
- 722-727
- OpenAlex
- W2921230249
- Cited by
- 27
- References
- 2
- FWCI
- 0.85
- Type
- conference paper
- 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.