Detecting high-quality GAN-generated face images using neural networks

Nowroozi, Ehsan and Mekdad, Yassine (2023) Detecting high-quality GAN-generated face images using neural networks. In: Maleh, Yassine and Alazab, Mamoun and Tawalbeh, Lo’ai and Romdhani, Imed, (eds.) Big Data Analytics and Intelligent Systems for Cyber Threat Intelligence. River Publishers, pp. 235-252. ISBN 9788770227780 (Print) 9788770227773 (Online)

This is the latest version of this item.

Full text not available from this repository. (Request a copy)


In the past decades, the excessive use of the last-generation Generative Adversarial Network (GAN) models in computer vision has enabled the creation of artificial face images that are visually indistinguishable from genuine ones. These images are particularly used in adversarial settings to create fake social media accounts and other fake online profiles. Such malicious activities can negatively impact the trustworthiness of users' identities. On the other hand, the recent development of GAN models may create high-quality face images without evidence of spatial artifacts. Therefore, reassembling uniform color channel correlations is a challenging research problem. To face these challenges, we need to develop efficient tools able to differentiate between fake and authentic face images. In this chapter, we propose a new strategy to differentiate GAN-generated images from authentic images by leveraging spectral band discrepancies, focusing on artificial face image synthesis. In particular, we enable the digital preservation of face images using the cross-band co-occurrence matrix and spatial co-occurrence matrix. Then, we implement these techniques and feed them to a convolutional neural network (CNN) architecture to identify the real from artificial faces. Additionally, we show that the performance boost is particularly significant and achieves more than 92% in different postprocessing environments. Finally, we provide several research observations demonstrating that this strategy improves a comparable detection method based only on intra-band spatial co-occurrences.
Item Type: Book Section / Chapter
Uncontrolled Keywords: Adversarial learning; Adversarial multimedia forensics; Convolutional neural networks; Cybersecurity.; DeepFake; Generative adversarial networks; Machine and deep learning
Divisions: Faculty of Engineering and Natural Sciences
Depositing User: Ehsan Nowroozi
Date Deposited: 08 Aug 2023 19:58
Last Modified: 08 Aug 2023 19:58

Available Versions of this Item

Actions (login required)

View Item
View Item