基于多线索痕迹指纹协同挖掘的可解释性伪造信息检测  

Interpretable Forgery Information Detection Based on Multi-Clue Marks Fingerprint Coordinated Mining

作　　者：郑威 凌霞 ZHENG Wei;LING Xia(China Information and Communication Research Institute,Beijing 100083,China)

机构地区：[1]中国信息通信研究院,北京100083

出　　处：《信息与电脑》2023年第14期154-156,共3页Information & Computer

摘　　要：随着信息技术的迅速发展和互联网的普及,伪造信息的产生和传播已成为一个严重的社会问题。传统的鉴伪检测方法往往局限于单一的特征或数据类型,无法满足复杂多样的伪造手段和技术。本文提出了一种基于多线索痕迹指纹协同挖掘的可解释性伪造信息检测方法,旨在解决多模态信息的伪造检测和定位问题。With the rapid development of information technology and the popularization of the Internet,the generation and dissemination of forgery information has become a serious social problem.Traditional pseudo-testing methods are often limited to single features or data types,and cannot meet complex and diverse forgery methods and technologies.This article proposes a method of explanatory information detection method based on multi-clue marks and fingerprint coordinated mining,which aims to solve the problem of fake detection and positioning of multi-modal information.

关 键 词：多线索痕迹指纹 可解释性 伪造信息检测 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]