# A One-Class Classifier for the Detection of GAN Manipulated Multi-Spectral Satellite Images

arXiv: https://arxiv.org/abs/2305.11795 · HTML: https://mlsanity.com/paper/2305.11795/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 38 references that are in the map.
- First posted on arXiv 19 May 2023.

## Builds on (most cited first, 19 of 19)

- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [An Introduction to Variational Autoencoders](https://mlsanity.com/paper/1906.02691/) (2019)
- [Object Detection with Deep Learning: A Review](https://mlsanity.com/paper/1807.05511/) (2018)
- [Autoencoding beyond pixels using a learned similarity metric](https://mlsanity.com/paper/1512.09300/) (2015)
- [Are GAN generated images easy to detect? A critical analysis of the state-of-the-art](https://mlsanity.com/paper/2104.02617/) (2021)
- [Deep Learning in Bioinformatics](https://mlsanity.com/paper/1603.06430/) (2016)
- [Manipulation Detection in Satellite Images Using Vision Transformer](https://mlsanity.com/paper/2105.06373/) (2021)
- [Satellite Image Forgery Detection and Localization Using GAN and One-Class Classifier](https://mlsanity.com/paper/1802.04881/) (2018)
- [Synthesizing Optical and SAR Imagery From Land Cover Maps and Auxiliary Raster Data](https://mlsanity.com/paper/2011.11314/) (2020)
- [Geo-DefakeHop: High-Performance Geographic Fake Image Detection](https://mlsanity.com/paper/2110.09795/) (2021)
- [Manipulation Detection in Satellite Images Using Deep Belief Networks](https://mlsanity.com/paper/2004.12441/) (2020)
- [Splicing Detection and Localization In Satellite Imagery Using Conditional GANs](https://mlsanity.com/paper/2205.01805/) (2022)
- [Multimodal and multicontrast image fusion via deep generative models](https://mlsanity.com/paper/2303.15963/) (2023)

## Built on by (most cited first, 1 of 1)

- [Deepfake Media Forensics: State of the Art and Challenges Ahead](https://mlsanity.com/paper/2408.00388/) (2024)

## Abstract (arXiv)

The highly realistic image quality achieved by current image generative models has many academic and industrial applications. To limit the use of such models to benign applications, though, it is necessary that tools to conclusively detect whether an image has been generated synthetically or not are developed. For this reason, several detectors have been developed providing excellent performance in computer vision applications, however, they can not be applied as they are to multispectral satellite images, and hence new models must be trained. In general, two-class classifiers can achieve very good detection accuracies, however they are not able to generalise to image domains and generative models architectures different than those used during training. For this reason, in this paper, we propose a one-class classifier based on Vector Quantized Variational Autoencoder 2 (VQ-VAE 2) features to overcome the limitations of two-class classifiers. First, we emphasize the generalization problem that binary classifiers suffer from by training and testing an EfficientNet-B4 architecture on multiple multispectral datasets. Then we show that, since the VQ-VAE 2 based classifier is trained only on pristine images, it is able to detect images belonging to different domains and generated by architectures that have not been used during training. Last, we compare the two classifiers head-to-head on the same generated datasets, highlighting the superiori generalization capabilities of the VQ-VAE 2-based detector.