通信学报 ›› 2020, Vol. 41 ›› Issue (6): 128-138.doi: 10.11959/j.issn.1000-436x.2020122

• 学术论文 • 上一篇    下一篇

基于样本增强的网络恶意流量智能检测方法

陈铁明,金成强,吕明琪,朱添田   

  1. 浙江工业大学计算机科学与技术学院,浙江 杭州 310023
  • 修回日期:2019-12-18 出版日期:2020-06-25 发布日期:2020-07-04
  • 作者简介:陈铁明(1978- ),男,浙江诸暨人,博士,浙江工业大学教授、博士生导师,主要研究方向为网络空间安全、大数据分析|金成强(1995- ),男,浙江温州人,浙江工业大学硕士生,主要研究方向为信息安全|吕明琪(1981- ),男,浙江杭州人,博士,浙江工业大学副教授,主要研究方向为数据挖掘与普适计算|朱添田(1992- ),男,浙江慈溪人,博士,浙江工业大学讲师,主要研究方向为网络安全、系统安全
  • 基金资助:
    国家自然科学基金资助项目(61202282);国家自然科学基金资助项目(61772026);国家自然科学基金与浙江省政府联合项目(U1509214)

Intelligent detection method on network malicious traffic based on sample enhancement

Tieming CHEN,Chengqiang JIN,Mingqi LYU,Tiantian ZHU   

  1. School of Computer Science and Technology,Zhejiang University of Technology,Hangzhou 310023,China
  • Revised:2019-12-18 Online:2020-06-25 Published:2020-07-04
  • Supported by:
    The National Natural Science Foundation of China(61202282);The National Natural Science Foundation of China(61772026);Joint Project of National Natural Science Foundation and Zhejiang Provincial Government(U1509214)

摘要:

为解决现有网络流量异常检测方法需要投喂大量数据且泛化能力较差的问题,提出了基于样本增强的网络恶意流量智能检测方法。所提方法从训练集中提取关键词,且基于关键词回避策略对训练集进行样本增强,提高了方法提取文本特征的能力。实验结果表明,所提方法通过小型训练数据集即可提高网络流量异常检测模型的准确率与跨数据集检测能力,相较于其他方法,在显著降低计算复杂度的同时得到了更佳的检测能力。

关键词: 样本增强, 异常检测, 流量检测, 机器学习

Abstract:

To address the problem that the existing methods of network traffic anomaly detection not only need a large number of training sets,but also have poor generalization ability,an intelligent detection method on network malicious traffic based on sample enhancement was proposed.The key words were extracted from the training set and the sample of the training set was enhanced based on the strategy of key word avoidance,and the ability for the method to extract the text features from the training set was improved.The experimental results show that,the accuracy of network traffic anomaly detection model and cross dataset can be significantly improved by small training set.Compared with other methods,the proposed method can reduce the computational complexity and achieve better detection ability.

Key words: sample enhancement, anomaly detection, traffic detection, machine learning

中图分类号: 

No Suggested Reading articles found!