信息安全研究2025，Vol.11Issue(4)：377-384,8.DOI:10.12379/j.issn.2096-1057.2025.04.11
基于数据增强的多模态虚假信息检测框架研究
Research on Data-enhanced Multi-modal False Information Detection Framework
刘宇栋 1黄千里 1王恒 1范洁1
作者信息
- 1. 北京电子科技学院网络空间安全系 北京 100070
- 折叠
摘要
Abstract
With the development of multimedia technology,rumor spreaders tend to create false information with multi-modal content to attract the attention of news readers.However,it is challenging to extract features from sparsely annotated multi-modal data and effectively integrate implicit clues in the multi-modal data to generate vector representations of false information.To address this issue,we propose a DEMF(data-enhanced multi-modal false information detection framework).DEMF leverages the advantages of pre-trained models and data augmentation techniques to reduce reliance on annotated data;it utilizes multi-level modal feature extraction and fusion to simultaneously capture fine-grained element-level relationships and coarse-grained modal-level relationships,in order to fully extracting multi-modal clues.Experiments on real-world datasets show that DEMF significantly outperforms state-of-the-art baseline models.关键词
虚假信息检测/多模态/深度学习/数据增强/预训练Key words
false information detection/multi-modal/deep learning/data augmentation/pre-trained分类
信息技术与安全科学引用本文复制引用
刘宇栋,黄千里,王恒,范洁..基于数据增强的多模态虚假信息检测框架研究[J].信息安全研究,2025,11(4):377-384,8.
