# CNN Detection of GAN-Generated Face Images based on Cross-Band Co-occurrences Analysis

arXiv: https://arxiv.org/abs/2007.12909 · HTML: https://mlsanity.com/paper/2007.12909/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jul 2020.

## Built on by (most cited first, 30 of 42)

- [Are GAN generated images easy to detect? A critical analysis of the state-of-the-art](https://mlsanity.com/paper/2104.02617/) (2021)
- [PatchCraft: Exploring Texture Patch for Efficient AI-generated Image Detection](https://mlsanity.com/paper/2311.12397/) (2023)
- [Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation](https://mlsanity.com/paper/2503.14905/) (2025)
- [Countering Malicious DeepFakes: Survey, Battleground, and Horizon](https://mlsanity.com/paper/2103.00218/) (2021)
- [Detecting GAN-generated Images by Orthogonal Training of Multiple CNNs](https://mlsanity.com/paper/2203.02246/) (2022)
- [Perceptual Artifacts Localization for Image Synthesis Tasks](https://mlsanity.com/paper/2310.05590/) (2023)
- [Evading DeepFake Detectors via Adversarial Statistical Consistency](https://mlsanity.com/paper/2304.11670/) (2023)
- [FakeBench: Probing Explainable Fake Image Detection via Large Multimodal Models](https://mlsanity.com/paper/2404.13306/) (2024)
- [Improving Synthetically Generated Image Detection in Cross-Concept Settings](https://mlsanity.com/paper/2304.12053/) (2023)
- [Forensic Analysis of Synthetically Generated Western Blot Images](https://mlsanity.com/paper/2112.08739/) (2021)
- [Forensic Self-Descriptions Are All You Need for Zero-Shot Detection, Open-Set Source Attribution, and Clustering of AI-generated Images](https://mlsanity.com/paper/2503.21003/) (2025)
- [Geo-DefakeHop: High-Performance Geographic Fake Image Detection](https://mlsanity.com/paper/2110.09795/) (2021)
- [Towards Robust GAN-generated Image Detection: a Multi-view Completion Representation](https://mlsanity.com/paper/2306.01364/) (2023)
- [Artifact Feature Purification for Cross-domain Detection of AI-generated Images](https://mlsanity.com/paper/2403.11172/) (2024)
- [Distinguishing Natural and Computer-Generated Images using Multi-Colorspace fused EfficientNet](https://mlsanity.com/paper/2110.09428/) (2021)
- [Passive Deepfake Detection Across Multi-modalities: A Comprehensive Survey](https://mlsanity.com/paper/2411.17911/) (2024)
- [SPRINT: Robust Model Attribution of Generated Images via Secret Pixel Reconstruction](https://mlsanity.com/paper/2508.05691/) (2025)
- [Face2Parts: Exploring Coarse-to-Fine Inter-Regional Facial Dependencies for Generalized Deepfake Detection](https://mlsanity.com/paper/2603.26036/) (2026)
- [Do Not Deceive Your Employer with a Virtual Background: A Video Conferencing Manipulation-Detection System](https://mlsanity.com/paper/2106.15130/) (2021)
- [Model Discrepancy Learning: Synthetic Faces Detection Based on Multi-Reconstruction](https://mlsanity.com/paper/2504.07382/) (2025)
- [Diversity Matters: Dataset Diversification and Dual-Branch Network for Generalized AI-Generated Image Detection](https://mlsanity.com/paper/2603.27800/) (2026)
- [Holistic Image Manipulation Detection using Pixel Co-occurrence Matrices](https://mlsanity.com/paper/2104.05693/) (2021)
- [Seam Carving Detection and Localization using Two-Stage Deep Neural Networks](https://mlsanity.com/paper/2109.01764/) (2021)
- [Leveraging Ensembles and Self-Supervised Learning for Fully-Unsupervised Person Re-Identification and Text Authorship Attribution](https://mlsanity.com/paper/2202.03126/) (2022)
- [Fighting Malicious Media Data: A Survey on Tampering Detection and Deepfake Detection](https://mlsanity.com/paper/2212.05667/) (2022)
- [Tex-ViT: A Generalizable, Robust, Texture-based dual-branch cross-attention deepfake detector](https://mlsanity.com/paper/2408.16892/) (2024)
- [Spritz-PS: Validation of Synthetic Face Images Using a Large Dataset of Printed Documents](https://mlsanity.com/paper/2304.02982/) (2023)
- [Explainable Artifacts for Synthetic Western Blot Source Attribution](https://mlsanity.com/paper/2409.18881/) (2024)
- [Autonomous and Self-Adapting System for Synthetic Media Detection and Attribution](https://mlsanity.com/paper/2504.03615/) (2025)
- [Frequency Bias Matters: Diving into Robust and Generalized Deep Image Forgery Detection](https://mlsanity.com/paper/2511.19886/) (2025)

## Abstract (arXiv)

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.