arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2308.16611cs.CV
收藏

检测新闻中图像-标题对的上下文外使用:一种反直觉的方法

Detecting Out-of-Context Image-Caption Pairs in News: A Counter-Intuitive Method

University of Bergen(卑尔根大学)

Eivind Moholdt, Sohail Ahmed Khan, Duc-Tien Dang-Nguyen

AI总结:

本文提出利用生成图像模型检测新闻中图像-标题对的上下文外使用,构建两个含6800张图像的数据集,并评估生成模型与相似度方法,以促进廉价伪造检测研究。

摘要:

社交媒体和新闻中错误信息与重新语境化媒体的增长,导致对事实核查方法的需求日益增加。与此同时,生成模型的进步使得廉价伪造和深度伪造既更容易制作,也更难以检测。在本文中,我们提出了一种新颖的方法,利用生成图像模型来检测新闻中图像-标题对的上下文外(OOC)使用。我们提出了两个新数据集,共包含使用两种不同生成模型生成的6800张图像,包括(1)DALL-E 2和(2)Stable-Diffusion。我们相信,本文提出的方法可以进一步推动生成模型在廉价伪造检测领域的研究,并且所得数据集可用于训练和评估旨在检测廉价伪造的新模型。我们进行了初步的定性和定量分析,以评估每个图像生成模型在此任务中的性能,并评估了几种计算图像相似度的方法。

英文摘要:

The growth of misinformation and re-contextualized media in social media and news leads to an increasing need for fact-checking methods. Concurrently, the advancement in generative models makes cheapfakes and deepfakes both easier to make and harder to detect. In this paper, we present a novel approach using generative image models to our advantage for detecting Out-of-Context (OOC) use of images-caption pairs in news. We present two new datasets with a total of $6800$ images generated using two different generative models including (1) DALL-E 2, and (2) Stable-Diffusion. We are confident that the method proposed in this paper can further research on generative models in the field of cheapfake detection, and that the resulting datasets can be used to train and evaluate new models aimed at detecting cheapfakes. We run a preliminary qualitative and quantitative analysis to evaluate the performance of each image generation model for this task, and evaluate a handful of methods for computing image similarity.

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。

↑