基于深度神经网络的配资网站识别研究
作者:
作者单位:

四川大学网络空间安全学院

作者简介:

通讯作者:

中图分类号:

TP391.1

基金项目:


Research on financing websites identification based on deep neural network
Author:
Affiliation:

School of Cyber Science and Engineering, Sichuan University

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    随着互联网金融的迅速发展,配资类网站给人们的财产安全造成的威胁日趋严重.而传统的恶意网站识别技术只适用于部分特征显著的网站识别,导致对配资网站的识别效果不佳.本文从多个维度选取特征,将识别特征归纳为域名特征、搜索引擎收录特征、标签特征、图片特征和文本特征五大类,较好地体现了配资网站与其他类别网站的本质不同,并结合深度神经网络,建立配资网站识别模型.为验证该模型的有效性,论文设计了深度神经网络模型与决策树算法、支持向量机算法、K-邻近算法的对比实验.从实验中发现,基于深度神经网络的配资网站识别模型提高了配资网站的识别准确率,模型准确率达到95.9%,精确率达到98.7%,各类评估指标效果均优于传统的机器学习算法.实验结果表明,该方法能有效地识别配资网站.

    Abstract:

    With the rapid development of Internet Finance, the existence of financing websites has become a much more serious problem for personal property safety. However, the traditional website recognition technology is only applicable to the website identification with some remarkable features, resulting in low efficiency of financing websites detection. This paper selects features from multiple dimensions and summarizes detection features into five categories: domain name features, search engines index features, tag features, image features, textual features, which greatly reflect the essential difference between the financing websites and other types of websites. Then a recognition model with deep neural network is proposed. In order to verify the validity of the model, a comparison experiment of our model with decision tree algorithm, support vector machine algorithm and K-Nearest Neighbor algorithm is designed. The experiments demonstrate that the accuracy and precision of the accuracy and precision of the proposed model is 95.9%, 98.7% respectively, and all kinds of evaluation indicators are better than the traditional machine learning algorithm. The results show that the proposed method can effectively detect the financing websites.

    参考文献
    相似文献
    引证文献
引用本文

引用本文格式: 何颖,杨频,王丛双,汤娟. 基于深度神经网络的配资网站识别研究[J]. 四川大学学报: 自然科学版, 2021, 58: 033003.

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2020-09-28
  • 最后修改日期:2020-10-19
  • 录用日期:2020-11-04
  • 在线发布日期: 2021-05-26
  • 出版日期: