基于貝葉斯和支持向量機的釣魚網(wǎng)站檢測方法
發(fā)布時間:2019-04-18 09:55
【摘要】:隨著電子商務和在線交易的不斷發(fā)展,釣魚網(wǎng)站已成為目前最難處理的網(wǎng)絡安全難題之一。提出了一種基于貝葉斯和不平衡支持向量機的釣魚網(wǎng)站檢測方法,首先提取待檢測網(wǎng)站的URL特征,采用改進貝葉斯方法進行分類檢測,如果不能明確分類,則提取該網(wǎng)站的頁面特征,并采用不平衡支持向量機方法進行分類檢測。實驗結果表明,與現(xiàn)有方法相比,方法所需的檢測時間少且能達到較高的檢測準確度。
[Abstract]:With the development of e-commerce and online transaction, phishing website has become one of the most difficult network security problems. In this paper, a new phishing website detection method based on Bayesian and unbalanced support vector machines is proposed. Firstly, the URL feature of the website to be detected is extracted, and the improved Bayesian method is used to classify and detect the phishing website. Then the page features of the website are extracted and the unbalanced support vector machine (SVM) is used for classification detection. The experimental results show that, compared with the existing methods, the detection time required by the method is shorter and the detection accuracy is higher.
【作者單位】: 常州大學信息科學與工程學院;
【基金】:國家自然科學基金(No.61070121)
【分類號】:TP393.08
[Abstract]:With the development of e-commerce and online transaction, phishing website has become one of the most difficult network security problems. In this paper, a new phishing website detection method based on Bayesian and unbalanced support vector machines is proposed. Firstly, the URL feature of the website to be detected is extracted, and the improved Bayesian method is used to classify and detect the phishing website. Then the page features of the website are extracted and the unbalanced support vector machine (SVM) is used for classification detection. The experimental results show that, compared with the existing methods, the detection time required by the method is shorter and the detection accuracy is higher.
【作者單位】: 常州大學信息科學與工程學院;
【基金】:國家自然科學基金(No.61070121)
【分類號】:TP393.08
【參考文獻】
相關期刊論文 前1條
1 劉萬里;劉三陽;薛貞霞;;不平衡支持向量機的平衡方法[J];模式識別與人工智能;2008年02期
【共引文獻】
相關期刊論文 前4條
1 趙小強;楊佳敏;;一種適應于不平衡數(shù)據(jù)集的改進TANC算法[J];蘭州理工大學學報;2014年05期
2 方景龍;王萬良;何偉成;;用于不平衡數(shù)據(jù)分類的FE-SVDD算法[J];計算機工程;2011年06期
3 彭晏飛;尚永剛;;基于樣本不平衡與視覺多樣性的超平面偏移法[J];計算機工程;2013年12期
4 王武功;馬榮國;;交通事件檢測的加權支持向量機算法[J];長安大學學報(自然科學版);2013年06期
相關博士學位論文 前5條
1 羅伊萍;LIDAR數(shù)據(jù)濾波和影像輔助提取建筑物[D];解放軍信息工程大學;2010年
2 薛貞霞;支持向量機及半監(jiān)督學習中若干問題的研究[D];西安電子科技大學;2009年
3 林智勇;基于核方法的不平衡數(shù)據(jù)學習[D];華南理工大學;2009年
4 朱霄s,
本文編號:2459956
本文鏈接:http://sikaile.net/guanlilunwen/ydhl/2459956.html
最近更新
教材專著