CNN Detection of GAN-Generated Face Images based on Cross-Band Co-occurrences Analysis
Open accessThe DOI matches its Crossref record; 27 of the 27 references it cites were found in a registry or an index.
Abstract
Last-generation GAN models allow to generate synthetic images which are visually indistinguishable from natural ones, raising the need to develop tools to distinguish fake and natural images thus contributing to preserve the trustworthiness of digital images. While modern GAN models can generate very high-quality images with no visible spatial artifacts, reconstruction of consistent relationships among colour channels is expectedly more difficult. In this paper, we propose a method for distinguishing GAN-generated from natural images by exploiting inconsistencies among spectral bands, with specific focus on the generation of synthetic face images. Specifically, we use cross-band co-occurrence matrices, in addition to spatial co-occurrence matrices, as input to a CNN model, which is trained to distinguish between real and synthetic faces. The results of our experiments confirm the goodness of our approach which outperforms a similar detection technique based on intra-band spatial co-occurrences only. The performance gain is particularly significant with regard to robustness against post-processing, like geometric transformations, filtering and contrast manipulations.
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.
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
“For instance, co-occurrences have been used for spotting subtle differences (usually not visible at human inspection) in the textural features of real versus manipulated natural images (through splicing) [32] and of real versus synthetic natural images [33], [34].”
From Forensic Analysis of Synthetically Generated Western Blot Images (2022) · cites this paper as [32]
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
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
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 1×
“The dataset used to train StyleGAN is the Flicker-Faces-HQ (FFHQ) database [23].”
MethodAnalyzing 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
An overview of gradient descent optimization algorithms
Ruder, S. (2016) · arXiv · doi:10.48550/arxiv.1609.04747 · Cited by 4,962
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
Contrast Limited Adaptive Histogram Equalization
Zuiderveld, K. (1994) · Graphics Gems · doi:10.1016/b978-0-12-336156-1.50061-6 · Cited by 4,192
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
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
Rich Models for Steganalysis of Digital Images
Fridrich, J., & Kodovsky, J. (2012) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2012.2190402 · Cited by 2,144 · cited 2×
“More specifically, the Subtractive Pixel Adjacency Matrix (SPAM) features [16], the rich feature model (SRMQ) [17] and the rich features models for color images (CSRMQ) [18], initially proposed for steganalysis, are usually considered by these methods.”
Method
Research works printed but not linked: 2
- goodfellow, 2014, Generative adversarial nets, Advances in Neural Information Processing Systems 27, 2672
- 10.1109/cvpr.2019.00453 · DOI · Paper page
Cited by
PatchCraft: Exploring Texture Patch for Efficient AI-generated Image DetectionPreprint
Zhong, N., Xu, Y., Li, S., Qian, Z., & Zhang, X. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2311.12397 · Cited by 227
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
“Barni et al. (2020) propose exploiting the inconsistencies among spectral bands, then a CNN model is trained with cross-band co-occurrence matrices and pixel co-occurrence matrices for discriminating real and fake faces.”
BackgroundAbbas, F., & Taeihagh, A. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.124260 · Cited by 184
FakeTagger: Robust Safeguards against DeepFake Dissemination via Provenance Tracking
Wang, R., Juefei-Xu, F., Luo, M., Liu, Y., & Wang, L. (2021) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3474085.3475518 · Cited by 135
Metadata
- Authors
- Barni, M., Kallas, K., Nowroozi, E., & Tondi, B.
- Affiliations
- University of Siena (IT)
- Venue
- 2020 IEEE International Workshop on Information Forensics and Security (WIFS)
- Publisher
- IEEE
- Published
- 2020-12-06
- Pages
- 1-6
- ISSN
- 2157-4774 (ISSN-L)
- OpenAlex
- W3044151627
- Cited by
- 103
- References
- 26
- Citations by year
- 2026: 13 · 2025: 18 · 2024: 21 · 2023: 21 · 2022: 21 · 2021: 5 · 2020: 4
- FWCI
- 3.93
- 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)
- HAL (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 › Image and Video Quality Assessment
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Keywords
- GAN-generated image detection, synthetic face images, convolutional neural networks, 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: CNN Detection of GAN-Generated Face Images based on Cross-Band Co-occurrences Analysis. https://app.cochat.ai/papers/10.1109/wifs49906.2020.9360905
- The paper
- Barni, M., Kallas, K., Nowroozi, E., & Tondi, B. (2020). CNN Detection of GAN-Generated Face Images based on Cross-Band Co-occurrences Analysis. 2020 IEEE International Workshop on Information Forensics and Security (WIFS). https://doi.org/10.1109/wifs49906.2020.9360905
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.