X-Transfer: A Transfer Learning-Based Framework for GAN-Generated Fake Image Detection

TL;DR

This paper introduces X-Transfer, a transfer learning framework utilizing dual neural networks and combined loss functions to effectively detect GAN-generated fake images, outperforming existing methods across multiple datasets.

Contribution

The paper presents a novel transfer learning-based detection algorithm with interleaved gradient transmission and combined loss functions, improving accuracy and generality in fake image detection.

Findings

Achieves up to 99.04% detection accuracy

Outperforms general transfer approaches by approximately 10%

Demonstrates effectiveness on both facial and non-face datasets

Abstract

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.