基于非合作动态博弈的网络安全主动防御技术研究.pdfVIP

计算机研 究与发展 rna1ofComputerResearchandDevelopment ISSCN11-1777门rP 48(2)：306—3l6，20l1 基于非合作动态博弈的网络安全主动防御技术研究 林旺群 王 慧 刘家红 邓 镭 李爱平 吴泉源 贾 焰 (国防科学技术大学计算机学 院 长沙 410073) (1inwangqun@nudt．edu．cn) Research on Active Defense Technology in Network Security Based on Non- CooperativeDynamicGam eTheory LinWangqun，WangHui，LiuJiahong，DengLei，LiAiping，WuQuanyuan，andJiaYan (CollegeofComputer，NationalUniversityofDefenseTechnology，Changsha410073) Abstract Game theory，an importantpartofartificialintelligenttechnique，hasbeen applied on network defensevery wel1．Staticmodelhasbeen used widely in mostoftheprevious studies ． However，somework showssuchmodelcannotfollow theevolvingofthestrategies0fattackers ． In thispaper，an activedefensemodelbasedon dynamicgametheoryofnon—cooperativeandcomplete informationhasbeengiven，thatis，theattack—defensegametreehasbeengeneratedbyadding some virtualnodeson theoriginalattack—defensegraph ． Based on theattack—defensegametree，thebest defense strategies are achieved under current network environm ent through resolving the Nash equilibrium in different situations． Besides， for the scenarios with complete information and incomplete information， two algorithms have been proposed respectively ． The analysis and experimentalresultsshow thatthe complexityofthealgorithmscan beguaranteed notworsethan othersim ilar works． Moreover， not only for scenario with complete information。but also in incompletecases，the sensib