摘要： 提出一种基于域名信息的钓鱼URL探测方法。使用编辑距离寻找与已知正常域名相似的域名，根据域名信息提取域名单词最大匹配特征、域名分割特征和URL分割特征，利用上述特征训练分类器，由此判断其他URL是否为钓鱼URL。在真实数据集上的实验结果表明，该方法钓鱼URL正确检测率达94%。

关键词: 钓鱼攻击, 钓鱼URL探测, 域名, 支持向量机, 编辑距离

Abstract: This paper proposes a phishing URL detection method. It uses edit distance to find the domain names similar to normal domain names. According to domain name information, domain word maximum match features, domain name segmentation features and URL segmentation features are extracted to train a classifier, which can detect whether the URL is a phishing URL. Experiments on the real data set show that the method can achieve a precision of 94%.

Key words: phishing attack, phishing URL detection, domain name, Support Vector Machine(SVM), edit distance

中图分类号: 

• TP393