arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2211.00680cs.CV
收藏

关于扩散模型产生的合成图像的检测

On the detection of synthetic images generated by diffusion models

University Federico II of Naples(那不勒斯费德里科二世大学);NVIDIA(英伟达)

Riccardo Corvi, Davide Cozzolino, Giada Zingarini, Giovanni Poggi, Koki Nagano, Luisa Verdoliva

摘要:

在过去的十年中,在创建合成媒体方面取得了巨大的进步,这主要归功于基于生成对抗网络(GAN)的强大方法的发展。最近,基于扩散模型(DM)的方法已经获得了关注。除了提供令人印象深刻的照相现实主义水平外,它们还可以创建基于文本的视觉内容,在从艺术到视频游戏的许多不同应用领域开辟新的令人兴奋的机会。另一方面,这种属性是恶意用户手中的额外资产,他们可以生成和分发完全适应其攻击的虚假媒体,这对媒体取证社区构成了新的挑战。通过这项工作,我们试图了解区分由扩散模型生成的合成图像与原始图像的难度,以及当前最先进的检测器是否适合这项任务。为此,我们首先暴露扩散模型留下的取证痕迹,然后研究为GAN生成的图像开发的当前检测器如何在这些新的合成图像上执行,特别是在涉及图像压缩和加密的具有挑战性的社交网络场景中。数据集和代码可在github.com/grip-unina/DMimageDetection上获得。

英文摘要:

Over the past decade, there has been tremendous progress in creating synthetic media, mainly thanks to the development of powerful methods based on generative adversarial networks (GAN). Very recently, methods based on diffusion models (DM) have been gaining the spotlight. In addition to providing an impressive level of photorealism, they enable the creation of text-based visual content, opening up new and exciting opportunities in many different application fields, from arts to video games. On the other hand, this property is an additional asset in the hands of malicious users, who can generate and distribute fake media perfectly adapted to their attacks, posing new challenges to the media forensic community. With this work, we seek to understand how difficult it is to distinguish synthetic images generated by diffusion models from pristine ones and whether current state-of-the-art detectors are suitable for the task. To this end, first we expose the forensics traces left by diffusion models, then study how current detectors, developed for GAN-generated images, perform on these new synthetic images, especially in challenging social-networks scenarios involving image compression and resizing. Datasets and code are available at github.com/grip-unina/DMimageDetection.

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。

↑