作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2013, Vol. 39 ›› Issue (5): 132-135. doi: 10.3969/j.issn.1000-3428.2013.05.028

• 安全技术 • 上一篇    下一篇

不均衡数据集下基于SVM的托攻击检测方法

吕成戍a,王维国b   

  1. (东北财经大学 a. 管理科学与工程学院;b. 数学与数量经济学院,辽宁 大连 116025)
  • 收稿日期:2012-05-29 出版日期:2013-05-15 发布日期:2013-05-14
  • 作者简介:吕成戍(1979-),女,讲师、博士研究生,主研方向:机器学习,电子商务,信息安全;王维国,教授、博士
  • 基金资助:
    辽宁省社会科学规划基金资助项目(L10BJL026)

Shilling Attack Detection Method Based on SVM Under Unbalanced Datasets

LV Cheng-shu a, WANG Wei-guo b   

  1. (a. School of Management Science and Engineering; b. School of Mathematics and Quantitative Economics, ongbei University of Finance and Economics, Dalian 116025, China)
  • Received:2012-05-29 Online:2013-05-15 Published:2013-05-14

摘要: 传统支持向量机(SVM)方法在数据不均衡情况下无法有效实现托攻击检测。在研究SVM的基础上,提出一种基于欠采样和代价敏感SVM相结合的托攻击检测方法。利用边界样本修剪技术实现训练样本的均衡,在消除部分多数类样本显著减小数据不均衡程度的同时,保证信息损失最小。结合受试者工作特征分析技术,利用代价敏感SVM对重构后的样本集进行训练,在限定范围内自动搜索最优参数,进而调节阈值获得系统决策函数。实验结果表明,该方法能提高托攻击的检测精度。

关键词: 攻击检测, 不均衡数据集, 代价敏感学习, 欠采样, 支持向量机, 接收机工作特性分析

Abstract: Traditional Support Vector Machine(SVM) drops significantly when it is applied to the problem of learning from unbalanced datasets. Based on the study of SVA, a new classifying method which combines the method of under-sampling and cost-sensitive SVM together is proposed. In the first stage, balanced data are set by reconstructing both the majority and the minority class. And in the second stage, cost sensitive SVM is conducted for detection decision function. Receiver Operating Characteristic(ROC) analysis is used to select optimum parameters of cost sensitive SVM in limited grid scope. The proposed model is used for attack detection on recommender systems. Experimental results show that the proposed method can improve the classification accuracy.

Key words: attack detection, unbalanced dataset, cost-sensitive learning, under-sampling, Support Vector Machine(SVM), Receiver Operating Characteristic(ROC) analysis

中图分类号: