Fighting Deepfakes by Detecting GAN DCT Anomalies
Open accessThe DOI matches its Crossref record; 58 of the 58 references it cites were found in a registry or an index.
Abstract
To properly contrast the Deepfake phenomenon the need to design new Deepfake detection algorithms arises; the misuse of this formidable A.I. technology brings serious consequences in the private life of every involved person. State-of-the-art proliferates with solutions using deep neural networks to detect a fake multimedia content but unfortunately these algorithms appear to be neither generalizable nor explainable. However, traces left by Generative Adversarial Network (GAN) engines during the creation of the Deepfakes can be detected by analyzing ad-hoc frequencies. For this reason, in this paper we propose a new pipeline able to detect the so-called GAN Specific Frequencies (GSF) representing a unique fingerprint of the different generative architectures. By employing Discrete Cosine Transform (DCT), anomalous frequencies were detected. The β statistics inferred by the AC coefficients distribution have been the key to recognize GAN-engine generated data. Robustness tests were also carried out in order to demonstrate the effectiveness of the technique using different attacks on images such as JPEG Compression, mirroring, rotation, scaling, addition of random sized rectangles. Experiments demonstrated that the method is innovative, exceeds the state of the art and also give many insights in terms of explainability.
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
Figures









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.
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?
The cited source says what the claim attributes to it.
In the citing paper
“Current state-of-the-art (SOTA) methods have proven to be very effective in detecting deepfake content generated by GAN architectures [93,94,95] and Diffusion Models (DMs) [96,97], demonstrating the ability to specialize not only in recognizing the architecture but also in identifying the specific pattern within the creation process.”
From Deepfake Media Forensics: Status and Future Challenges (2025) · cites this paper as [95]
The cited source says what the claim attributes to it.
In the citing paper
“For instance, a pipeline to detect GAN specific traces left during the deepfake creation is proposed in Giudice et al. (2021).”
From Deepfakes: current and future trends (2024) · cites this paper as Giudice et al. (2021)
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
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
Book Review: Pattern Recognition and Machine Learning
Nasrabadi, N. M. (2007) · Journal of Electronic Imaging · doi:10.1117/1.2819119 · Cited by 22,066
Labaca-Castro, R. (2023) · Machine Learning under Malware Attack · doi:10.1007/978-3-658-40442-0_9 · Cited by 19,272
GAN(Generative Adversarial Nets)
(2017) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.29.5_177_2 · Cited by 19,270
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
A 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 5×
“For the sake of comparisons in our scenario we evaluated pristine images generated by StarGAN [16], AttGAN [19], GDWCT [20], StyleGAN [17], StyleGAN2 [18], and genuine images extracted by CelebA [21] and FFHQ.”
BackgroundMethodInfluentialPattern Recognition and Machine Learning
(2007) · Kybernetes · doi:10.1108/03684920710743466 · Cited by 8,265
Deep Learning Face Attributes in the Wild
Liu, Z., Luo, P., Wang, X., & Tang, X. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.425 · Cited by 7,747
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
Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope
Oliva, A., & Torralba, A. (2001) · International Journal of Computer Vision · doi:10.1023/a:1011139631724 · Cited by 6,319
Context Encoders: Feature Learning by Inpainting
Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., & Efros, A. A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.278 · Cited by 5,691
Progressive 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
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
Scene Parsing through ADE20K Dataset
Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., & Torralba, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.544 · Cited by 3,326
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 4×
“The authors used in the experiments CELEBA [21] and FFHQ (https://github.com/NVlabs/ffhq-dataset, accessed on 14/02/2021) images (real datasets of faces) and compared Fakespotter with Zhang et al. [5] obtaining an average detection accuracy of more than 90% on the four types of fake faces: Entire Synthesis [27], [18],…”
BackgroundMethodInfluentialThe expectation-maximization algorithm
Moon, T. K. (1996) · IEEE Signal Processing Magazine · doi:10.1109/79.543975 · Cited by 3,181
Dlib-ml: A Machine Learning Toolkit
King, D. E. (2009) · doi:10.5555/1577069.1755843 · Cited by 2,777
Presentation and validation of the Radboud Faces Database
Langner, O., Dotsch, R., Bijlstra, G., Wigboldus, D. H. J., Hawk, S. T., & van Knippenberg, A. (2010) · Cognition and Emotion · doi:10.1080/02699930903485076 · Cited by 2,420
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial NetworksPreprint
Zhu, J.-Y., Park, T., Isola, P., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.10593 · Cited by 2,278
Celeb-DF: A Large-Scale Challenging Dataset for DeepFake Forensics
Li, Y., Yang, X., Sun, P., Qi, H., & Lyu, S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00327 · Cited by 1,846 · cited 1×
“[5] obtaining an average detection accuracy of more than 90% on the four types of fake faces: Entire Synthesis [27], [18], Attribute Editing [16], [29], Expression Manipulation [17], [29], DeepFake [30], [31].”
BackgroundFace2Face: 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
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
Diverse Image-to-Image Translation via Disentangled Representations
Lee, H.-Y., Tseng, H.-Y., Huang, J.-B., Singh, M., & Yang, M.-H. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01246-5_3 · Cited by 1,225
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
Vaccari, C., & Chadwick, A. (2020) · Social Media + Society · doi:10.1177/2056305120903408 · Cited by 978
AttGAN: 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 14×
“Different Deepfake images were generated considering StarGAN, GDWCT, AttGAN, StyleGAN and StyleGAN2 architectures.”
MethodInfluentialA mathematical analysis of the DCT coefficient distributions for images
Lam, E. Y., & Goodman, J. W. (2000) · IEEE Transactions on Image Processing · doi:10.1109/83.869177 · Cited by 707
Detecting 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 4×
“In [3], it has been already demonstrated that it is possible to attack and retrieve the signature on the network’s de-convolutional layers; in this paper a method to identify any anomaly of the generated “fake” signal, only partially highlighted in some preliminary studies [4], [5] is presented.”
InfluentialLearning in the Frequency Domain
Xu, K., Qin, M., Sun, F., Wang, Y., Chen, Y.-K., & Ren, F. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00181 · Cited by 563
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
STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing
Liu, M., Ding, Y., Xia, M., Liu, X., Ding, E., Zuo, W., & Wen, S. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00379 · Cited by 394
DeepFake Detection by Analyzing Convolutional Traces
Guarnera, L., Giudice, O., & Battiato, S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00341 · Cited by 374 · cited 2×
“In [3], it has been already demonstrated that it is possible to attack and retrieve the signature on the network’s de-convolutional layers; in this paper a method to identify any anomaly of the generated “fake” signal, only partially highlighted in some preliminary studies [4], [5] is presented.”
BackgroundMethodSelf-citationThe Embedding Hypothesis: From Fourier Circuits to No-Q Attention
Rigoni, N. (2026) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.19273886 · Cited by 292
Training Behavior of Deep Neural Network in Frequency Domain
Xu, Z.-Q. J., Zhang, Y., & Xiao, Y. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-36708-4_22 · Cited by 255
FakeSpotter: A Simple yet Robust Baseline for Spotting AI-Synthesized Fake Faces
Wang, R., Juefei-Xu, F., Ma, L., Xie, X., Huang, Y., Wang, J., & Liu, Y. (2020) · Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2020/476 · Cited by 250
A Face and Palmprint Recognition Approach Based on Discriminant DCT Feature Extraction
Jing, X.-Y., & Zhang, D. (2004) · IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics) · doi:10.1109/tsmcb.2004.837586 · Cited by 241
Unmasking DeepFakes with simple Features
Durall, R., Keuper, M., Pfreundt, F.-J., & Keuper, J. (2019) · arXiv · doi:10.48550/arxiv.1911.00686 · Cited by 184
BAM! The Behance Artistic Media Dataset for Recognition Beyond Photography
Wilber, M. J., Fang, C., Jin, H., Hertzmann, A., Collomosse, J., & Belongie, S. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.136 · Cited by 154
Image-To-Image Translation via Group-Wise Deep Whitening-And-Coloring Transformation
Cho, W., Choi, S., Park, D. K., Shin, I., & Choo, J. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01089 · Cited by 154 · cited 3×
“Another style transfer approach is the work of Cho et al. [20], proposing a group-wise deep whitening-and coloring method (GDWCT) for a better styling capacity.”
Fighting Deepfake by Exposing the Convolutional Traces on Images
Guarnera, L., Giudice, O., & Battiato, S. (2020) · IEEE Access · doi:10.1109/access.2020.3023037 · Cited by 149
Self-citationOn the Spectral Bias of Neural Networks
Rahaman, N., Baratin, A., Arpit, D., Draxler, F., Lin, M., Hamprecht, F. A., Bengio, Y., & Courville, A. C. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.08734 · Cited by 139
Semantic segmentation of images exploiting DCT based features and random forest
Ravì, D., Bober, M. Z., Farinella, G. M., Guarnera, M., & Battiato, S. (2015) · Pattern Recognition · doi:10.1016/j.patcog.2015.10.021 · Cited by 82
Self-citationA Fourier Perspective on Model Robustness in Computer Vision
Yin, D., Lopes, R. G., Shlens, J., Cubuk, E. D., & Gilmer, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.08988 · Cited by 80
Representing scenes for real-time context classification on mobile devices
Farinella, G. M., Ravì, D., Tomaselli, V., Guarnera, M., & Battiato, S. (2014) · Pattern Recognition · doi:10.1016/j.patcog.2014.05.014 · Cited by 46
Self-citationDetecting and Simulating Artifacts in GAN Fake ImagesPreprint
Zhang, X., Karaman, S., & Chang, S.-F. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.06515 · Cited by 39
FakeSpotter: A Simple Baseline for Spotting AI-Synthesized Fake Faces
Wang, R., Ma, L., Juefei-Xu, F., Xie, X., Wang, J., & Liu, Y. (2019) · Cited by 39
Preliminary Forensics Analysis of DeepFake Images
Guarnera, L., Giudice, O., Nastasi, C., & Battiato, S. (2020) · 2020 AEIT International Annual Conference (AEIT) · doi:10.23919/aeit50178.2020.9241108 · Cited by 38
Self-citationAnalysis of the DCT Coefficient Distributions for Document Coding
Lam, E. Y. M. (2004) · IEEE Signal Processing Letters · doi:10.1109/lsp.2003.821789 · Cited by 36
Camera model identification based on DCT coefficient statistics
Thai, T. H., Retraint, F., & Cogranne, R. (2015) · Digital Signal Processing · doi:10.1016/j.dsp.2015.01.002 · Cited by 34
FakeSpotter: A Simple yet Robust Baseline for Spotting AI-Synthesized Fake FacesPreprint
Wang, R., Juefei-Xu, F., Ma, L., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.06122 · Cited by 32
Detecting GANs and Retouching based Digital Alterations via DAD-HCNN
Jain, A., Majumdar, P., Singh, R., & Vatsa, M. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00344 · Cited by 29
Global Texture Enhancement for Fake Face Detection in the WildPreprint
Liu, Z., Qi, X., & Torr, P. H. S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.00133 · Cited by 27
(2020) · doi:10.1109/cvprw50498.2020.00329 · Cited by 18
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
Learning in the Frequency DomainPreprint
Xu, K. M., Qin, M., Sun, F., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.12416 · Cited by 15
Cited by
Masood, M., Nawaz, M., Malik, K. M., Javed, A., Irtaza, A., & Malik, H. (2023) · Applied Intelligence · doi:10.1007/s10489-022-03766-z · Cited by 543
Deep Learning for Deepfakes Creation and Detection: A Survey
Nguyen, T. T., Nguyen, Q. V. H., Nguyen, D. T., Nguyen, D. T., Huynh-The, T., Nahavandi, S., Nguyen, T. T., Pham, Q.-V., & Nguyen, C. M. (2019) · arXiv · doi:10.48550/arxiv.1909.11573 · Cited by 464
Deep learning for deepfakes creation and detection: A survey
Nguyen, T. T., Nguyen, Q. V. H., Nguyen, D. T., Nguyen, D. T., Huynh-The, T., Nahavandi, S., Nguyen, T. T., Pham, Q.-V., & Nguyen, C. M. (2022) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2022.103525 · Cited by 464
“[180] in which they use discrete cosine transform statistics to detect so-called specific GAN frequencies to differentiate between real images and deepfakes.”
Combining EfficientNet and Vision Transformers for Video Deepfake Detection
Coccomini, D. A., Messina, N., Gennaro, C., & Falchi, F. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-06433-3_19 · Cited by 296
Deepfakes: current and future trends
Gambín, Á. F., Yazidi, A., Vasilakos, A., Haugerud, H., & Djenouri, Y. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-023-10679-x · Cited by 145
Metadata
- Authors
- Giudice, O., Guarnera, L., & Battiato, S.
- Affiliations
- University of Catania (IT)
- Corresponding author
- Giudice, Oliver
- Venue
- Journal of Imaging
- Publisher
- MDPI AG
- Published
- 2021-07-30
- Volume
- 7
- Issue
- 8
- Pages
- 128
- ISSN
- 2313-433X (ISSN-L)
- PMC
- PMC8404913
- OpenAlex
- W3122852338
- Cited by
- 118
- References
- 58
- Citations by year
- 2026: 17 · 2025: 32 · 2024: 29 · 2023: 20 · 2022: 16 · 2021: 4
- FWCI
- 6.20
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Journal of Imaging (publishedVersion, cc-by)
- Europe PMC (PubMed Central) (publishedVersion, other-oa)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- 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 › Computer Vision and Pattern Recognition › Advanced Steganography and Watermarking Techniques
- Keywords
- deepfake detection, generative adversarial networks, discrete cosine transform, explainable AI, robustness to image attacks, image forgery detection
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.