Are GAN generated images easy to detect? A critical analysis of the state-of-the-art
It addresses the problem of distinguishing fake media for internet security and misinformation prevention, but is incremental as it reviews and compares existing methods.
The paper analyzes state-of-the-art methods for detecting synthetic images generated by GANs, focusing on performance comparisons across existing architectures and challenging real-world scenarios like social media uploads.
The advent of deep learning has brought a significant improvement in the quality of generated media. However, with the increased level of photorealism, synthetic media are becoming hardly distinguishable from real ones, raising serious concerns about the spread of fake or manipulated information over the Internet. In this context, it is important to develop automated tools to reliably and timely detect synthetic media. In this work, we analyze the state-of-the-art methods for the detection of synthetic images, highlighting the key ingredients of the most successful approaches, and comparing their performance over existing generative architectures. We will devote special attention to realistic and challenging scenarios, like media uploaded on social networks or generated by new and unseen architectures, analyzing the impact of suitable augmentation and training strategies on the detectors' generalization ability.