# Detection, Attribution and Localization of GAN Generated Images

arXiv: https://arxiv.org/abs/2007.10466 · HTML: https://mlsanity.com/paper/2007.10466/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jul 2020.

## Built on by (most cited first, 24 of 24)

- [Preserving Fairness Generalization in Deepfake Detection](https://mlsanity.com/paper/2402.17229/) (2024)
- [Countering Malicious DeepFakes: Survey, Battleground, and Horizon](https://mlsanity.com/paper/2103.00218/) (2021)
- [Eyes Tell All: Irregular Pupil Shapes Reveal GAN-generated Faces](https://mlsanity.com/paper/2109.00162/) (2021)
- [GAN-generated Faces Detection: A Survey and New Perspectives](https://mlsanity.com/paper/2202.07145/) (2022)
- [Robust Attentive Deep Neural Network for Exposing GAN-generated Faces](https://mlsanity.com/paper/2109.02167/) (2021)
- [Bridging the Gap Between Ideal and Real-world Evaluation: Benchmarking AI-Generated Image Detection in Challenging Scenarios](https://mlsanity.com/paper/2509.09172/) (2025)
- [Beyond Deepfake Images: Detecting AI-Generated Videos](https://mlsanity.com/paper/2404.15955/) (2024)
- [Model Attribution of Face-swap Deepfake Videos](https://mlsanity.com/paper/2202.12951/) (2022)
- [On the Exploitation of Deepfake Model Recognition](https://mlsanity.com/paper/2204.04513/) (2022)
- [Methods and Trends in Detecting AI-Generated Images: A Comprehensive Review](https://mlsanity.com/paper/2502.15176/) (2025)
- [Open-Eye: An Open Platform to Study Human Performance on Identifying AI-Synthesized Faces](https://mlsanity.com/paper/2205.06680/) (2022)
- [DeePhy: On Deepfake Phylogeny](https://mlsanity.com/paper/2209.09111/) (2022)
- [Distinguishing Natural and Computer-Generated Images using Multi-Colorspace fused EfficientNet](https://mlsanity.com/paper/2110.09428/) (2021)
- [Generative Adversarial Networks and Other Generative Models](https://mlsanity.com/paper/2207.03887/) (2022)
- [Protect-Your-IP: Scalable Source-Tracing and Attribution against Personalized Generation](https://mlsanity.com/paper/2405.16596/) (2024)
- [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)
- [Fighting Malicious Media Data: A Survey on Tampering Detection and Deepfake Detection](https://mlsanity.com/paper/2212.05667/) (2022)
- [SeeTheSeams: Localized Detection of Seam Carving based Image Forgery in Satellite Imagery](https://mlsanity.com/paper/2108.12534/) (2021)
- [Transferable Class-Modelling for Decentralized Source Attribution of GAN-Generated Images](https://mlsanity.com/paper/2203.09777/) (2022)
- [Fingerprints of Super Resolution Networks](https://mlsanity.com/paper/2410.21653/) (2024)
- [Improving Generalization in Deepfake Detection with Face Foundation Models and Metric Learning](https://mlsanity.com/paper/2508.19730/) (2025)
- [Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization](https://mlsanity.com/paper/2509.07993/) (2025)
- [Representation and Reference Selection in Training-Free Synthetic Image Attribution](https://mlsanity.com/paper/2607.12052/) (2026)

## Abstract (arXiv)

Recent advances in Generative Adversarial Networks (GANs) have led to the creation of realistic-looking digital images that pose a major challenge to their detection by humans or computers. GANs are used in a wide range of tasks, from modifying small attributes of an image (StarGAN [14]), transferring attributes between image pairs (CycleGAN [91]), as well as generating entirely new images (ProGAN [36], StyleGAN [37], SPADE/GauGAN [64]). In this paper, we propose a novel approach to detect, attribute and localize GAN generated images that combines image features with deep learning methods. For every image, co-occurrence matrices are computed on neighborhood pixels of RGB channels in different directions (horizontal, vertical and diagonal). A deep learning network is then trained on these features to detect, attribute and localize these GAN generated/manipulated images. A large scale evaluation of our approach on 5 GAN datasets comprising over 2.76 million images (ProGAN, StarGAN, CycleGAN, StyleGAN and SPADE/GauGAN) shows promising results in detecting GAN generated images.