主成分分析法的网页篡改检测  

Webpage tamper detection based on principal component analysis

作　　者：阮宏玮[1,2] 刘铁钢[1] 李华[1,2] 王小雨[1] 

机构地区：[1]内蒙古大学计算机学院,呼和浩特010021 [2]内蒙古大学网络信息中心,呼和浩特010021

出　　处：《中国科技论文》2012年第7期544-547,共4页China Sciencepaper

基　　金：国家自然科学基金资助项目(60863015);教育部春晕项目(Z2007-1-01032);内蒙古自然基金资助项目(2011MS0912);内蒙古高等学校科学研究项目(NJ09012

摘　　要：通过介绍网页在生活和应用中的重要性,说明网页篡改的主要方法以及特点。针对网页属性选取的规范化程度不高,规则不清晰和检测工作量很大等问题,提出对网页属性进行分类,对不同分类的属性采取适应性针对性规则处理方法,在保证效率的基础上实现降维处理,以减轻检测压力。提出利用主成分分析法对网页属性进行分类和规范化,并基于此提出指导性的实现网页防篡改检测系统规则。This paper introduces the importance of webpages and their applications, as well as the main ways of tampering webpages and their characteristics. Given the low level of webpage properties selection standardization, unclear roles and heavy workload of detection, we propose to classify the webpage properties. By dealing with different categories of properties in adaptive and targeted ways, we can reduce the dimension to alleviate the pressure of detection while ensuring efficiency. For this purpose, we use principal component analysis to classify and standardize the webpage properties, and then intrxtuce the guidance rules for achieving the page tamper detection

关 键 词：网页篡改 主成分分析 属性分类 文本检测 

分 类 号：TP393.092[自动化与计算机技术—计算机应用技术]