基于智能进化算法的DDoS攻击检测防御研究
    点此下载全文
引用本文:李 萌.基于智能进化算法的DDoS攻击检测防御研究[J].计算技术与自动化,2021,(2):110-117
摘要点击次数: 565
全文下载次数: 0
作者单位
李 萌 (国家药品监督管理总局信息中心, 北京 100044) 
中文摘要:为了减少分布式拒绝服务攻击(DDoS),将蚂蚱优化算法(GOA)与机器学习算法结合使用,通过创建入侵检测系统(IDS)来满足监控环境的要求,并能够区分正常和攻击流量。所设计的基于GOA的IDS技术(GOIDS)能够从原始IDS数据集中选择最相关的特征来帮助区分典型的低速DDoS攻击,然后将选择的特征传递给支持向量机(SVM)、决策树(DT)、朴素贝叶斯(NB)和多层感知器(MLP)等分类器来识别攻击类型。利用KDD Cup 99和CIC-IDS 2017公开数据集作为实验数据,仿真结果表明,基于决策树的GOIDS具有较高的检测率和较低的假阳性率。
中文关键词:进化算法  DDos  入侵检测系统  KDD-Cup 99  支持向量机
 
Research on DDoS Attack Detection and Defense Based on intelligent Evolutionary Algorithm
Abstract:In order to reduce distributed denial of service attacks (DDoS), this paper combines the grasshopper optimization algorithm (GOA) and machine learning algorithm to create an intrusion detection system (IDS) to meet the requirements of monitoring environment, and can distinguish between normal and attack traffic. The designed Goa based IDS technology (goids) can select the most relevant features from the original IDS data set to help distinguish the typical low-speed DDoS attacks, and then pass the selected features to support vector machine (SVM), decision tree (DT), naive Bayes (NB) and multi-layer perceptron (MLP) and other classifiers to identify the types of attacks. Using KDD cup 99 and cic-ids 2017 open data set as experimental data, the simulation results show that the decision tree based goids has high detection rate and low false-positive rate.
keywords:evolutionary algorithm  DDoS  intrusion detection system  KDD cup 99  support vector machine
查看全文   查看/发表评论   下载pdf阅读器