arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.08783cs.CVcs.AIcs.CL
收藏

图像-文本上下文外检测:利用合成多模态虚假信息

Image-Text Out-Of-Context Detection Using Synthetic Multimodal Misinformation

The Graduate University for Advanced Studies, SOKENDAI(综合研究大学院大学(SOKENDAI));National Institute of Informatics(情报学研究所);The University of Tokyo(东京大学)

Fatma Shalabi, Huy H. Nguyen, Hichem Felouat, Ching-Chun Chang, Isao Echizen

AI总结:

针对多模态虚假信息,提出基于合成数据生成的图像-文本上下文外检测方法,创建专用数据集并开发高效检测器,实验验证其有效性。

摘要:

虚假信息已成为数字信息日益增长时代的一大挑战,亟需开发有效的检测方法。我们研究了一种新颖的上下文外检测(OOCD)方法,该方法利用合成数据生成技术。我们创建了一个专门针对OOCD设计的数据集,并开发了一个高效的检测器以实现准确分类。我们的实验结果验证了合成数据生成的有效性,并证明了其在解决OOCD数据局限性方面的功效。该数据集和检测器应能为未来研究及开发稳健的虚假信息检测系统提供宝贵资源。

英文摘要:

Misinformation has become a major challenge in the era of increasing digital information, requiring the development of effective detection methods. We have investigated a novel approach to Out-Of-Context detection (OOCD) that uses synthetic data generation. We created a dataset specifically designed for OOCD and developed an efficient detector for accurate classification. Our experimental findings validate the use of synthetic data generation and demonstrate its efficacy in addressing the data limitations associated with OOCD. The dataset and detector should serve as valuable resources for future research and the development of robust misinformation detection systems.

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。

↑