有限次重复博弈下的网络攻击行为研究  

Behavior Model of Network Attacker in Finite Repeated Games

作　　者：彭伟[1] 刘晓明[1] 彭辉[1] 余沛毅[1] 

机构地区：[1]解放军理工大学指挥信息系统学院军事信息学教研中心,江苏南京210007

出　　处：《指挥与控制学报》2015年第4期476-479,共4页Journal of Command and Control

基　　金：江苏省自然科学基金(BK2011120)资助~~

摘　　要：网络攻防博弈在很多情况下是多回合的较量,可以从有限次重复博弈的角度来对攻击者的行为进行建模,从而更好地预测攻击者可能采取的策略.在分析攻击者行为的基础上,根据攻击者的理性级别将攻击者分为4种类型:长远近视攻击者、长远老练攻击者、短期近视攻击者、短期老练攻击者,然后基于强化学习、EWA、QRE等理论和方法分别针对这4种不同类型的攻击者构建了行为模型,并给出了模型的参数估计,最后通过试验对模型的有效性和准确性进行了验证.The turns of network attack-defense are usually more than once, so it is a good idea to establish the behavior model of network attacker in finite repeated games, and it can help to predict the decision of network attacker more accurately. The behavior of network attackers is analyzed, and attackers are classified as four types according to the rational level, such as long-term myopic, long-term sophisticated, short-term myopic, and short-term sophisticated. Then based on the theories of reinforcement learning, Experience-Weighted Attraction （EWA）, Quantal Response Equilibrium（QRE） and so on, four different behavior models are established, and parameter assessment of models is also finished. Finally the experiment result validates the effectiveness and accurateness of models.

关 键 词：重复博弈 网络攻击 EWA模型 行为模型 QRE 

分 类 号：TP393.08[自动化与计算机技术—计算机应用技术]