Incremental learning for the detection and classification of GAN-generated images
This work tackles the problem of adapting detection methods to evolving GAN-generated content, which is crucial for security and media integrity, but it is incremental as it builds on existing deep learning solutions.
The paper addresses the challenge of detecting and classifying GAN-generated images, particularly human faces, by proposing an incremental learning approach that adapts to new GAN architectures, achieving correct discrimination in experiments with multiple GANs.
Current developments in computer vision and deep learning allow to automatically generate hyper-realistic images, hardly distinguishable from real ones. In particular, human face generation achieved a stunning level of realism, opening new opportunities for the creative industry but, at the same time, new scary scenarios where such content can be maliciously misused. Therefore, it is essential to develop innovative methodologies to automatically tell apart real from computer generated multimedia, possibly able to follow the evolution and continuous improvement of data in terms of quality and realism. In the last few years, several deep learning-based solutions have been proposed for this problem, mostly based on Convolutional Neural Networks (CNNs). Although results are good in controlled conditions, it is not clear how such proposals can adapt to real-world scenarios, where learning needs to continuously evolve as new types of generated data appear. In this work, we tackle this problem by proposing an approach based on incremental learning for the detection and classification of GAN-generated images. Experiments on a dataset comprising images generated by several GAN-based architectures show that the proposed method is able to correctly perform discrimination when new GANs are presented to the network