AI vs. AI: Can AI Detect AI-Generated Images?

Abstract

The proliferation of Artificial Intelligence (AI) models such as Generative Adversarial Networks (GANs) has shown impressive success in image synthesis. Artificial GAN-based synthesized images have been widely spread over the Internet with the advancement in generating naturalistic and photo-realistic images. This might have the ability to improve content and media; however, it also constitutes a threat with regard to legitimacy, authenticity, and security. Moreover, implementing an automated system that is able to detect and recognize GAN-generated images is significant for image synthesis models as an evaluation tool, regardless of the input modality. To this end, we propose a framework for reliably detecting AI-generated images from real ones through Convolutional Neural Networks (CNNs). First, GAN-generated images were collected based on different tasks and different architectures to help with the generalization. Then, transfer learning was applied. Finally, several Class Activation Maps (CAM) were integrated to determine the discriminative regions that guided the classification model in its decision. Our approach achieved 100% on our dataset, i.e., Real or Synthetic Images (RSI), and a superior performance on other datasets and configurations in terms of its accuracy. Hence, it can be used as an evaluation tool in image generation. Our best detector was a pre-trained EfficientNetB4 fine-tuned on our dataset with a batch size of 64 and an initial learning rate of 0.001 for 20 epochs. Adam was used as an optimizer, and learning rate reduction along with data augmentation were incorporated.

Optimally Configured Generative Adversarial Networks to Distinguish Real and AI- Generated Human Faces

“…It covers human decision-making, facial recognition, and factors influencing face memorization. Baraheem et al (2023) developed a framework using convolutional neural networks to distinguish AI-generated images from actual ones. They used transfer learning and Class Activation Maps to identify discriminative cues.…”

“…The method achieved 100% accuracy on a dataset, with EfficientNetB4 being the best detector. Adam was used as an optimizer Baraheem and Nguyen (2023).…”