摘要: 针对钓鱼式网络攻击,从URL入手,对网址URL和Web页面内容综合特征进行识别、分类,实现网络钓鱼检测并保证检测的效率和精度。用支持向量机主动学习算法和适合小样本集的分类模型提高分类性能。实验结果证明,网络钓鱼检测系统能达到较高的检测 精度。
关键词:
网络钓鱼,
支持向量机,
主动学习算法,
分类器,
敏感特征
Abstract: To detect and prevent various kinds of phishing attacks, there are many different preventive strategies and detective ideas. This paper takes the research of URL as the point of departure, describes how to detect phishing through the identification classification of the integrated features of URL and Web page content so as to ensure the efficiency and accuracy of detection. In the decision of the classification algorithm, it chooses Support Vector Machine(SVM) active learning algorithm which adapts to the small sample set of the classification model and achieves the ideal performance of the classification. Experimental results show that the system can achieve higher detection accuracy and performance with a small sample of the classification model training set.
Key words:
phishing,
Support Vector Machine(SVM),
active learning algorithm,
classifier,
sensitive characteristic
中图分类号:
何高辉, 邹福泰, 谭大礼, 王明政. 基于SVM主动学习算法的网络钓鱼检测系统[J]. 计算机工程, 2011, 37(19): 126-128.
HE Gao-Hui, JU Fu-Tai, TAN Da-Li, WANG Meng-Zheng. Phishing Detection System Based on SVM Active Learning Algorithm[J]. Computer Engineering, 2011, 37(19): 126-128.