基于再生成的训练无关文生图模型伪造图像溯源方法
Regeneration Based Training-free Attribution of Fake Images Generated by Text-to-Image Generative Models
AI总结：
提出一种无需训练的再生成溯源方法，通过反演提示词并在候选模型中重生成图像，依据相似度排序确定伪造图像来源，性能媲美SOTA且具高扩展性和鲁棒性。
摘要：
文本到图像生成模型因其能够根据提示描述生成图像的能力，近来受到了广泛关注。尽管这些模型展现出了良好的性能，但人们对其生成的伪造图像可能被滥用的担忧也随之而来。针对这一问题，我们提出了一种简单而有效的、无需训练的归属方法，用于将文本到图像模型生成的伪造图像归因于其源模型。对于给定的待归属测试图像，我们首先反演该图像的文本提示，然后将重建的提示输入到不同的候选模型中，以重新生成候选伪造图像。通过计算并排序测试图像与候选图像之间的相似度，我们可以确定图像的来源。这种归属机制使得模型所有者能够对其模型的任何滥用行为负责。需要注意的是，我们的方法不限制候选文本到图像生成模型的数量。综合实验表明：（1）我们的方法能够有效地将伪造图像归因于其源模型，达到了与最先进方法相当的归属性能；（2）我们的方法具有高度的可扩展性，能够很好地适应现实世界中的归属场景；（3）所提出的方法对常见攻击（如高斯模糊、JPEG压缩和缩放）具有令人满意的鲁棒性。我们还分析了影响归属性能的因素，并探讨了所提方法作为插件在提升现有最先进方法性能方面所带来的增益。我们希望我们的工作能为解决AI生成图像的来源问题提供一些思路，并防止文本到图像生成模型的滥用。
英文摘要：
Text-to-image generative models have recently garnered significant attention due to their ability to generate images based on prompt descriptions. While these models have shown promising performance, concerns have been raised regarding the potential misuse of the generated fake images. In response to this, we have presented a simple yet effective training-free method to attribute fake images generated by text-to-image models to their source models. Given a test image to be attributed, we first inverse the textual prompt of the image, and then put the reconstructed prompt into different candidate models to regenerate candidate fake images. By calculating and ranking the similarity of the test image and the candidate images, we can determine the source of the image. This attribution allows model owners to be held accountable for any misuse of their models. Note that our approach does not limit the number of candidate text-to-image generative models. Comprehensive experiments reveal that (1) Our method can effectively attribute fake images to their source models, achieving comparable attribution performance with the state-of-the-art method; (2) Our method has high scalability ability, which is well adapted to real-world attribution scenarios. (3) The proposed method yields satisfactory robustness to common attacks, such as Gaussian blurring, JPEG compression, and Resizing. We also analyze the factors that influence the attribution performance, and explore the boost brought by the proposed method as a plug-in to improve the performance of existing SOTA. We hope our work can shed some light on the solutions to addressing the source of AI-generated images, as well as to prevent the misuse of text-to-image generative models.
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。
