Identification of deep network generated images using disparities in color components
Open accessThe DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index.
Abstract
Abstract With the powerful deep network architectures, such as generative adversarial networks, one can easily generate photorealistic images. Although the generated images are not dedicated for fooling human or deceiving biometric authentication systems, research communities and public media have shown great concerns on the security issues caused by these images. This paper addresses the problem of identifying deep network generated (DNG) images. Taking the differences between camera imaging and DNG image generation into considerations, we analyze the disparities between DNG images and real images in different color components. We observe that the DNG images are more distinguishable from real ones in the chrominance components, especially in the residual domain. Based on these observations, we propose a feature set to capture color image statistics for identifying DNG images. Additionally, we evaluate several detection situations, including the training-testing data are matched or mismatched in image sources or generative models and detection with only real images. Extensive experimental results show that the proposed method can accurately identify DNG images and outperforms existing methods when the training and testing data are mismatched. Moreover, when the GAN model is unknown, our methods also achieves good performance with one-class classification by using only real images for training.
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
LIBSVM: A library for support vector machines
Chang, C.-C., & Lin, C.-J. (2011) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/1961189.1961199 · Cited by 40,918
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
Textural Features for Image Classification
Haralick, R. M., Shanmugam, K., & Dinstein, I. (1973) · IEEE Transactions on Systems, Man, and Cybernetics · doi:10.1109/tsmc.1973.4309314 · Cited by 22,886
Auto-Encoding Variational Bayes
Kingma, D. P., & Welling, M. (2013) · arXiv · doi:10.48550/arxiv.1312.6114 · Cited by 20,067
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
Ledig, C., Theis, L., Huszar, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., Wang, Z., et al. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.19 · Cited by 12,696
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 4×
“n ideal case, the generator eventually reproduces the distribution of real data, and the discriminator fails to distinguish between generated samples and real samples. Recently, many works [17]–[19], [23]–[25] have been proposed to improve the vanilla GAN. For example, Radford et al. [23] designed deep convolutional G…”
BackgroundMethodInfluentialA 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
Identity mappings in deep residual networks
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_38 · Cited by 10,741
Identity Mappings in Deep Residual Networks
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · arXiv · doi:10.48550/arxiv.1603.05027 · Cited by 10,665 · cited 3×
“58 ResNet v2-50 [60] 0.”
MethodInfluentialImproved training of Wasserstein GANs
Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., & Courville, A. (2017) · arXiv · doi:10.48550/arxiv.1704.00028 · Cited by 6,800 · cited 4×
“[36] made an improvement for Wasserstein GAN with gradient penalty (WGAN-GP).”
BackgroundMethodInfluential
Research works printed but not linked: 20
- Wang, 2019, Variational probabilistic generative framework for single image super-resolution, Signal Process., 156, 92, 10.1016/j.sigpro.2018.10.004 · DOI
- Korus, 2017, Digital image integrity–a survey of protection and verification techniques, Digit Signal Process, 71, 1, 10.1016/j.dsp.2017.08.009 · DOI
- Galbally, 2014, Biometric antispoofing methods: a survey in face recognition, IEEE Access, 2, 1530, 10.1109/ACCESS.2014.2381273 · DOI · Paper page
- Luo, 2010, JPEG Error analysis and its applications to digital image forensics, IEEE Trans. Inf. Forens. Secur., 5, 480, 10.1109/TIFS.2010.2051426 · DOI · Paper page
- Bianchi, 2012, Image forgery localization via block-grained analysis of JPEG artifacts, IEEE Trans. Inf. Forens. Secur., 7, 1003, 10.1109/TIFS.2012.2187516 · DOI · Paper page
- Chen, 2017, Detection of operation chain: JPEG-resampling-JPEG, Signal Process. Image Commun., 57, 8, 10.1016/j.image.2017.04.008 · doi:10.1016/j.image.2017.04.008
- Zhang, 2019, On the robustness of JPEG post-compression to resampling factor estimation, Signal Process., 107371
- Korus, 2016, Multi-scale fusion for improved localization of malicious tampering in digital images, IEEE Trans. Image Process., 25, 1312, 10.1109/TIP.2016.2518870 · DOI
- Li, 2017, Image forgery localization via integrating tampering possibility maps, IEEE Trans. Inf. Forens. Secur., 12, 1240, 10.1109/TIFS.2017.2656823 · DOI · Paper page
- Patel, 2016, Secure face unlock: spoof detection on smartphones, IEEE Trans. Inf. Forens. Secur., 11, 2268, 10.1109/TIFS.2016.2578288 · DOI · Paper page
- Boulkenafet, 2016, Face spoofing detection using colour texture analysis, IEEE Trans. Inf. Forens. Secur., 11, 1818, 10.1109/TIFS.2016.2555286 · DOI · Paper page
- Dang, 2018, Deep learning based computer generated face identification using convolutional neural network, Appl. Sci., 8, 2610, 10.3390/app8122610 · DOI · Paper page
- Wen, 2015, Face spoof detection with image distortion analysis, IEEE Trans. Inf. Forens. Secur., 10, 746, 10.1109/TIFS.2015.2400395 · DOI · Paper page
- Li, 2018, Identification of various image operations using residual-based features, IEEE Trans. Circuits Syst. Video Technol., 28, 31, 10.1109/TCSVT.2016.2599849 · DOI · Paper page
- Bayar, 2018, Constrained convolutional neural networks: a new approach towards general purpose image manipulation detection, IEEE Trans. Inf. Forens. Secur., 13, 2691, 10.1109/TIFS.2018.2825953 · DOI · Paper page
- D. Cozzolino, J. Thies, A. Rössler, C. Riess, M. Nießner, L. Verdoliva, Forensictransfer: weakly-supervised domain adaptation for forgery detection, arXiv:1812.02510. · arXiv
- F. Marra, C. Saltori, G. Boato, L. Verdoliva, Incremental learning for the detection and classification of GAN-generated images, arXiv:1910.01568. · arXiv
- F. Yu, A. Seff, Y. Zhang, S. Song, T. Funkhouser, J. Xiao, LSUN: Construction of a large-scale image dataset using deep learning with humans in the loop, arXiv:1506.03365. · arXiv
- K. Simonyan, A. Zisserman, Very deep convolutional networks for large-scale image recognition, arXiv:1409.1556. · arXiv
- Kodovsky, 2012, Ensemble classifiers for steganalysis of digital media, IEEE Trans. Inf. Forens. Secur., 7, 432, 10.1109/TIFS.2011.2175919 · DOI · Paper page
Cited by
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
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
Exploiting 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
Exposing DeepFake Videos By Detecting Face Warping Artifacts
Li, Y., & Lyu, S. (2018) · arXiv · doi:10.48550/arxiv.1811.00656 · Cited by 785
FakeCatcher: Detection of Synthetic Portrait Videos using Biological Signals
Ciftci, U. A., Demir, I., & Yin, L. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3009287 · Cited by 499
Global Texture Enhancement for Fake Face Detection in the Wild
Liu, Z., Qi, X., & Torr, P. H. S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00808 · Cited by 401
Do 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
Exploring Temporal Coherence for More General Video Face Forgery Detection
Zheng, Y., Bao, J., Chen, D., Zeng, M., & Wen, F. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01477 · Cited by 320
DeepFake Detection for Human Face Images and Videos: A Survey
Malik, A., Kuribayashi, M., Abdullahi, S. M., & Khan, A. N. (2022) · IEEE Access · doi:10.1109/access.2022.3151186 · Cited by 297
“[65] evaluated the statistical properties of deep network-generated images, such as the correlation between adjacent pixels in HSV and YCbCr color spaces, to distinguish DeepFake images.”
BackgroundCIFAKE: Image Classification and Explainable Identification of AI-Generated Synthetic Images
Bird, J. J., & Lotfi, A. (2024) · IEEE Access · doi:10.1109/access.2024.3356122 · Cited by 265
Are GAN Generated Images Easy to Detect? A Critical Analysis of the State-Of-The-Art
Gragnaniello, D., Cozzolino, D., Marra, F., Poggi, G., & Verdoliva, L. (2021) · 2021 IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme51207.2021.9428429 · Cited by 212
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
“As expected, systemically organized DeepFake datasets such as Face-Forensics++ (Rossler et al., 2019), Celeb-DF (Li et al., 2020e), DFDC (Dolhansky et al., 2020) as well as open-sourced high-fidelity face generation methods such as PGGAN (Karras et al., 2017), StarGAN (Choi et al., 2018), StyleGAN (Karras et al., 2019)…”
BackgroundMethodInfluentialUnmasking DeepFakes with simple Features
Durall, R., Keuper, M., Pfreundt, F.-J., & Keuper, J. (2019) · arXiv · doi:10.48550/arxiv.1911.00686 · Cited by 184
Fake face detection via adaptive manipulation traces extraction network
Guo, Z., Yang, G., Chen, J., & Sun, X. (2021) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2021.103170 · Cited by 165
Incremental learning for the detection and classification of GAN-generated images
Marra, F., Saltori, C., Boato, G., & Verdoliva, L. (2019) · 2019 IEEE International Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs47025.2019.9035099 · Cited by 154
A comprehensive overview of Deepfake: generation, detection, datasets, and opportunities
Seow, J. W., Lim, M. K., Phan, R. C. W., & Liu, J. K. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.09.135 · Cited by 149
Deepfakes Detection Techniques Using Deep Learning: A Survey
Almars, A. M. (2021) · Journal of Computer and Communications · doi:10.4236/jcc.2021.95003 · Cited by 143
A Robust GAN-Generated Face Detection Method Based on Dual-Color Spaces and an Improved Xception
Chen, B., Liu, X., Zheng, Y., Zhao, G., & Shi, Y.-Q. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3116679 · Cited by 125
“Regarding [18] and [26], although they consider other color spaces, they exploit only the chrominance components, discarding the luminance component.”
BackgroundMethodInfluentialCNN Detection of GAN-Generated Face Images based on Cross-Band Co-occurrences Analysis
Barni, M., Kallas, K., Nowroozi, E., & Tondi, B. (2020) · 2020 IEEE International Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs49906.2020.9360905 · Cited by 103
GAN-Generated Faces Detection: A Survey and New Perspectives
Wang, X., Guo, H., Hu, S., Chang, M.-C., & Lyu, S. (2023) · Frontiers in Artificial Intelligence and Applications · doi:10.3233/faia230558 · Cited by 98
The face deepfake detection challenge
Guarnera, L., Giudice, O., Guarnera, F., Ortis, A., Puglisi, G., Paratore, A., Bui, L. M. Q., Fontani, M., Coccomini, D. A., Caldelli, R., et al. (2022) · Journal of Imaging · doi:10.3390/jimaging8100263 · Cited by 79
“After the seminal work by Do et al. [13], which was entirely data-driven, other approaches followed where images are pre-processed (e.g., by high-pass filtering [14], or working on the chrominance components [15]) in order to let the network work on a facilitating domain.”
MethodDeepFake Detection Based on High-Frequency Enhancement Network for Highly Compressed Content
Gao, J., Xia, Z., Marcialis, G. L., Dang, C., Dai, J., & Feng, X. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.123732 · Cited by 67
Deepfake Video Detection Based on MesoNet with Preprocessing Module
Xia, Z., Qiao, T., Xu, M., Wu, X., Han, L., & Chen, Y. (2022) · Symmetry · doi:10.3390/sym14050939 · Cited by 56
Effective and Fast DeepFake Detection Method Based on Haar Wavelet Transform
Younus, M. A., & Hasan, T. M. (2020) · 2020 International Conference on Computer Science and Software Engineering (CSASE) · doi:10.1109/csase48920.2020.9142077 · Cited by 53
Towards DeepFake video forensics based on facial textural disparities in multi-color channels
Xia, Z., Qiao, T., Xu, M., Zheng, N., & Xie, S. (2022) · Information Sciences · doi:10.1016/j.ins.2022.06.003 · Cited by 47
Visual Deepfake Detection: Review of Techniques, Tools, Limitations, and Future Prospects
Ur Rehman Ahmed, N., Badshah, A., Adeel, H., Tajammul, A., Daud, A., & Alsahfi, T. (2025) · IEEE Access · doi:10.1109/access.2024.3523288 · Cited by 45
Rahman, M. A., Paul, B., Sarker, N. H., Hakim, Z. I. A., & Fattah, S. A. (2023) · 2023 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip49359.2023.10222083 · Cited by 34
“Color band inconsistencies [2] or lack of variation in color intensity [4] can act as unique identifiers for generative models.”
BackgroundShe, 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
“Other examples include using color and texture features [24], biosignal features [25], [26], and frequency domain features [27], [28].”
BackgroundDeepfakes Detection Methods: A Literature Survey
Weerawardana, M., & Fernando, T. (2021) · 2021 10th International Conference on Information and Automation for Sustainability (ICIAfS) · doi:10.1109/iciafs52090.2021.9606067 · Cited by 23
Detecting CNN-Generated Facial Images in Real-World Scenarios
Hulzebosch, N., Ibrahimi, S., & Worring, M. (2020) · arXiv · doi:10.48550/arxiv.2005.05632 · Cited by 18
(2020) · doi:10.1109/cvprw50498.2020.00329 · Cited by 18
National Institute of Standards and Technology (US) (2024) · doi:10.6028/nist.ai.100-4 · Cited by 9
Chrominance and Luminance: a study to detect deepfakes
Talib, M. A., Nasir, Q., Nassif, A. B., Fadhl, N. B., & Gouda, O. M. (2025) · Multimedia Tools and Applications · doi:10.1007/s11042-025-20618-3 · Cited by 5
“Another recent work [22] proposed an effective method to identify deep network images using multiple color components such as RGB , HSV , and YCbCr .”
Fourier spectrum discrepancies in deep network generated images
Dzanic, T., Shah, K., & Witherden, F. (2019) · arXiv · doi:10.48550/arxiv.1911.06465
Metadata
- Authors
- Li, H., Li, B., Tan, S., & Huang, J.
- Venue
- Signal Processing
- Publisher
- Elsevier BV
- Published
- 2020-09
- Volume
- 174
- Pages
- 107616
- ISSN
- 0165-1684 (ISSN-L)
- OpenAlex
- W2888519208
- Cited by
- 241
- References
- 26
- FWCI
- 12.27
- Type
- journal article
- Language
- en
- Open access
- green
- Licence
- www.elsevier.com/tdm/userlicense/1.0/ (tdm)
- www.elsevier.com/legal/tdmrep-license (tdm)
- Funders
- National Natural Science Foundation of China
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.