Rapid advances in Generative Adversarial Networks (GANs) raise new challenges for image attribution; detecting whether an image is synthetic and, if so, determining which GAN architecture created it. Uniquely, we present a solution to this task capable of 1) matching images invariant to their semantic content; 2) robust to benign transformations (changes in quality, resolution, shape, etc.) commonly encountered as images are re-shared online. In order to formalize our research, a challenging benchmark, Attribution88, is collected for robust and practical image attribution. We then propose RepMix, our GAN fingerprinting technique based on representation mixing and a novel loss. We validate its capability of tracing the provenance of GAN-generated images invariant to the semantic content of the image and also robust to perturbations. We show our approach improves significantly from existing GAN fingerprinting works on both semantic generalization and robustness. Data and code are available at https://github.com/TuBui/image_attribution.
翻译:创世对立网络(GANs)的快速进步带来了图像归属的新挑战; 发现图像是否合成,如果是的话, 确定哪些GAN结构是合成的。 独特的是, 我们为这项任务提出了一个解决方案, 能够(1) 将图像与其语义内容的变异相匹配;(2) 在图像重新在线共享时常见到的对良性转变( 质量、 分辨率、 形状等的变化) 。 为了将我们的研究正规化, 收集了一个具有挑战性的基准, 即 归国88, 以稳健和实用的图像归属。 然后我们提出 RepMix, 我们基于演示混合和新颖损失的GAN指纹技术。 我们验证其追踪GAN生成图像的变异源与图像的语义内容的源代码的能力, 并且能够对扰动。 我们展示了我们的方法, 与现有的GAN关于语义一般化和坚固度的指纹工作相比, 有了很大的改进。 数据和代码可以在 http://gitututubui/ image_ atritionatrition 上查阅 。