arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.04115cs.CV
收藏

T-GD:可转移的GAN生成图像检测框架

T-GD: Transferable GAN-generated Images Detection Framework

Sungkyunkwan University(成均馆大学)

Hyeonseong Jeon, Youngoh Bang, Junyaup Kim, Simon S. Woo

摘要:

生成对抗网络(GANs)的最新进展使得能够生成高度逼真的图像,这引起了人们对它们被滥用于恶意目的的担忧。检测这些GAN生成的图像(GAN图像)变得越来越具有挑战性,因为底层伪影和特定模式的显着减少。缺乏这种痕迹可能会阻碍检测算法识别GAN图像并转移知识以识别其他类型的GAN图像。在这项工作中,我们提出了可转移的GAN图像检测框架T-GD,这是一个强大的可转移框架,用于有效检测GAN图像。T-GD由教师和学生模型组成,可以迭代地相互教学和评估,以提高检测性能。首先,我们在源数据集上训练教师模型,并将其用作学习目标数据集的起点。为了训练学生模型,我们通过混合源数据集和目标数据集来注入噪声,同时约束权重变化以保持起点。我们的方法是一种自训练方法,但通过专注于提高GAN图像检测的可转移性,将其与现有方法区分开来。T-GD通过克服灾难性遗忘并有效地检测最先进的GAN图像来实现源数据集的高性能,这些图像只有少量数据而没有任何元数据信息。

英文摘要:

Recent advancements in Generative Adversarial Networks (GANs) enable the generation of highly realistic images, raising concerns about their misuse for malicious purposes. Detecting these GAN-generated images (GAN-images) becomes increasingly challenging due to the significant reduction of underlying artifacts and specific patterns. The absence of such traces can hinder detection algorithms from identifying GAN-images and transferring knowledge to identify other types of GAN-images as well. In this work, we present the Transferable GAN-images Detection framework T-GD, a robust transferable framework for an effective detection of GAN-images. T-GD is composed of a teacher and a student model that can iteratively teach and evaluate each other to improve the detection performance. First, we train the teacher model on the source dataset and use it as a starting point for learning the target dataset. To train the student model, we inject noise by mixing up the source and target datasets, while constraining the weight variation to preserve the starting point. Our approach is a self-training method, but distinguishes itself from prior approaches by focusing on improving the transferability of GAN-image detection. T-GD achieves high performance on the source dataset by overcoming catastrophic forgetting and effectively detecting state-of-the-art GAN-images with only a small volume of data without any metadata information.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑