一种自主免疫学习的分布式网络攻击对抗模型研究  

Distributed network attack against model with self-immunity learning

作　　者：蒋勇[1,2] 赵作鹏[2] 

机构地区：[1]江苏联合职业技术学院信息技术系,江苏徐州221008 [2]中国矿业大学计算机科学与技术学院,江苏徐州221008

出　　处：《计算机应用研究》2015年第4期1138-1140,共3页Application Research of Computers

基　　金：江苏省自然科学基金资助项目(BK2012129)

摘　　要：针对网络系统容易遭受网络病毒攻击的问题,提出一种自主免疫学习的分布式网络攻击对抗模型。该网络攻击对抗模型采用分布式网络攻击检测算法来计算数据包信任值,再通过设置信任值的检测阈值,当数据包的信任值低于阈值时,判断该数据包遭到攻击。此方法可以确定数据包是否遭到病毒入侵,并对病毒的危险等级进行评估。基于人体的病毒防御机理提出适用于网络的自主免疫机制,通过带抗体的特殊数据包来清除带病毒数据包,并基于病毒的危险等级来生产适当的特殊数据包数量。在实验仿真中,算法在检测网络病毒的攻击以及清除网络病毒方面表现出良好的效果。For the problems that network systems was easy to be attacked by network vulnerable,this paper proposed a distributed network attack against the model with self-immunity learning. The cyber-attacks against the model used a distributed network attack detection algorithms to calculate the trust value of the data packet case,then set the trust value of the detection threshold,when the trust value was below the threshold packet to determine the packet attack,this method could determine whether the packet was viruses and virus assess the level of danger presented for network self-defense mechanism of the human immune system-based virus,through a special data packet with antibodies to clear the packet with the virus,and based on the risk level of the virus to produce the appropriate number of special data packet. In the simulation experiments,the algorithm to detect network attacks and viruses clear network viruses show good results.

关 键 词：网络攻击 网络病毒 分布式网络攻击检测 自主免疫 

分 类 号：TP393.08[自动化与计算机技术—计算机应用技术]