X-Transfer: A Transfer Learning-Based Framework for GAN-Generated Fake Image Detection
This addresses security issues from deceptive image generation for applications like media forensics, though it is incremental as it builds on existing transfer learning methods.
The paper tackled the problem of detecting GAN-generated fake images, especially for security concerns like face replacement, by introducing the X-Transfer framework that enhances transfer learning with interleaved parallel gradient transmission and combined loss functions, achieving a best metric of 99.04% on facial datasets, which is about a 10% improvement over general transfer approaches.
Generative adversarial networks (GANs) have remarkably advanced in diverse domains, especially image generation and editing. However, the misuse of GANs for generating deceptive images, such as face replacement, raises significant security concerns, which have gained widespread attention. Therefore, it is urgent to develop effective detection methods to distinguish between real and fake images. Current research centers around the application of transfer learning. Nevertheless, it encounters challenges such as knowledge forgetting from the original dataset and inadequate performance when dealing with imbalanced data during training. To alleviate this issue, this paper introduces a novel GAN-generated image detection algorithm called X-Transfer, which enhances transfer learning by utilizing two neural networks that employ interleaved parallel gradient transmission. In addition, we combine AUC loss and cross-entropy loss to improve the model's performance. We carry out comprehensive experiments on multiple facial image datasets. The results show that our model outperforms the general transferring approach, and the best metric achieves 99.04%, which is increased by approximately 10%. Furthermore, we demonstrate excellent performance on non-face datasets, validating its generality and broader application prospects.