合成图像检测器的现状与未来发展

Present and Future Generalization of Synthetic Image Detectors

September 21, 2024

作者: Pablo Bernabeu-Perez, Enrique Lopez-Cuena, Dario Garcia-Gasulla

cs.AI

摘要

随着不断推出新的、更好的图像生成模型，对合成图像检测器的需求不断增加。在这样一个充满活力的领域中，检测器需要能够广泛泛化并且对未受控制的变化具有稳健性。本研究受到这种背景的启发，关注时间、图像转换和数据来源在检测器泛化中的作用。在这些实验中，没有一个评估过的检测器被发现是通用的，但结果表明一个集成模型可能是。在野外收集的数据上进行的实验表明，这一任务比大规模数据集定义的任务更具挑战性，指向实验和实际实践之间存在差距。最后，我们观察到一种竞争平衡效应，即更好的生成器导致更好的检测器，反之亦然。我们假设这推动了领域朝着生成器和检测器之间永远接近的竞赛方向发展。

English

The continued release of new and better image generation models increases the demand for synthetic image detectors. In such a dynamic field, detectors need to be able to generalize widely and be robust to uncontrolled alterations. The present work is motivated by this setting, when looking at the role of time, image transformations and data sources, for detector generalization. In these experiments, none of the evaluated detectors is found universal, but results indicate an ensemble could be. Experiments on data collected in the wild show this task to be more challenging than the one defined by large-scale datasets, pointing to a gap between experimentation and actual practice. Finally, we observe a race equilibrium effect, where better generators lead to better detectors, and vice versa. We hypothesize this pushes the field towards a perpetually close race between generators and detectors.