摘要
计算机网络安全的重要性毋庸置疑。随着以物联网技术为代表的第三代网络技术的兴起，计算机网络安全的研究又迎来了新的热潮。作为计算机网络安全的一项重要技术——入侵检测的研究也与时俱进，增加了许多新的研究内容。以生物免疫系统为基础的人工免疫理论近些年一直受到国内外专家学者的高度重视。作为其中主要的研究热点——基于免疫机制的入侵检测研究也一直是这些专家学者关注的重点。特别是对决定其检测性能的最主要部件——检测器的研究更加受到研究者的青睐。本文就以检测器为主要研究对象，以检测器存在的主要问题为突破口，以生物免疫机制和相关理论及方法为手段，重点讨论检测器优化和检测方法的改进。
检测器的维度与检测性能之间有着很大的关系，特别是在实值形态空间。针对实值空间高维检测器存在的黑洞、检测器高重叠等问题，借鉴线性矩阵变换的思想，利用主成分分析法，在保证足够信息量的前提下，将高维的实值空间转化为低维的主成分空间，并在主成分空间中进行亲和力函数和匹配规则设计，利用亲和力计算完成基于主成分的检测器分布优化处理，从而解决以上问题。实验验证在主成分空间里“变形”后的检测器可以在保证原有信息量损失不多的基础上较好地覆盖非自体空间，提升检测器的检测性能。
检测器分布优化一直以来都是国内外学者研究的热点。针对其中存在的诸多问题，特别是检测器分区和边界入侵问题，提出一种基于协同进化和Monte Carlo方法的检测器分布优化算法，首先利用V-detector算法的思想调整检测器检测半径来解决检测器的边界入侵问题，然后利用协同进化思想将检测器集合分成不同子集，通过子集间的相互作用进行优化，并采用Monte Carlo方法估计当前优化效果来判定是否达到预期目的。实验验证通过这两种方法的结合使得优化后的检测器更好地覆盖非自体空间，较好地解决黑洞和高重叠等问题。
DNA技术作为生物工程领域一项重要的技术已经在诸多领域发挥着重要作用。而检测器的多个属性可以被看做是不同的DNA组合，借以这一思想，提出一种基于DNA疫苗的检测器更新与生成模型，提取不同的有效基因构造DNA库，通过DNA库进行疫苗合成等方式来构造候选检测器，从而制造更多成熟有效的检测器。实验验证模型可使检测器实时更新，优化对非自体空间的覆盖，稳定其检测效果。
无论是二进制空间还是实值空间，单一检测器包含内容的不完备性使得检测器的检测效果一直都不甚理想。为了解决这一问题，借助免疫网络的思想和危险理论提出一种多形态检测模型，将系统的检测模块分成二进制模块和实值模块，并通过信号机制完成两个模块的协同检测。实验验证模型适应更复杂的待检测事件，使系统的检测效果在不同环境下都可以保持较为稳定的水平。
本文主要研究了基于免疫机制的入侵检测中检测器的优化与检测，针对其中存在的问题提出了相应的解决方法。以上研究内容不仅对基于免疫机制的入侵检测研究提供了许多新的方法，也对人工免疫理论及其应用起到了一定的拓宽研究范围的作用。
The importance of computer network security is undisputed. With the adventof the third generation of network technology represented by the Internet ofthings, computer network security ushered in a new wave of research. As animportant technology of computer network security, the intrusion detectionresearch also advances with the times, adding a number of new research contents.In recent years, the artificial immune theory, based on biological immune system,has been attracting great attention of domestic and foreign experts, in whichimmunity-based intrusion detection research has been the focus of researchers. Inparticular, the research of detector, the most important part to determine thedetection performance, is more favored by the researchers. This paper mainlydiscusses the improvement of detector optimization and detection method, takingthe detector as the research object, the existing problems of the detector as abreakthrough, the biological immune mechanism and other related theories andmethods as a mean.
The detector’s dimension has a significant relationship with the detectionperformance, especially in the real-valued shape space. For the hole, theoverlapping and other problems in high-dimensional detector, the research drawson the thought of linear matrix transformations and principal component analysis,transforms high-dimensional real-valued shape space into low-dimensionalprincipal component shape space under the premise to ensure an adequateamount of information, and then, designs affinity function and matching rules inthe principal component shape space. This research also applies affinitycalculation to do the principal-components detector distribution optimizationprocess to solve the above problems. The experiments verify that the detectors after deformation in the principal component shape space can ensure bettercoverage of nonself space and enhance the detection performance with little lossof the original amount of information.
The optimization of detector distribution has always been a hot issue amongthe domestic and foreign researchers. For the existing problems, particularly thedetectors’ multi areas and intrusions in the self/nonself boundary, a detectordistribution optimization algorithm is proposed which is based on co-evolutionand the Monte Carlo method: first, using the thought of the V-detector algorithmto adjust the detector’s detection radius in order to solve the intrusion problem inthe self/nonself boundary; then applying the co-evolution thought to divide thedetectors into different subsets and to do the optimization with the interactionbetween the subsets; and finally employing the Monte Carlo method to estimatethe current optimization effect to determine whether the anticipated results hasbeen achieved. Experiments validate that the optimized detectors make bettercoverage of nonself space and deal with the problems of holes and overlappingwell.
DNA technology, as an important technology in the bioengineering field, hasplayed an important role in many fields. Multiple attributes of the detector can beregarded as different combinations of DNA. Via this thought, the thesis proposesa detector update and generation model based on DNA vaccines, which is toconstruct the DNA pool by extracting different effective genes. Through the DNApool, the candidates are constructed by the vaccine synthesis. Thereby, more andmore mature and effective detectors will be created. Experiments verify thatmodel can update the detectors in real time, optimize the detector’s coverage innonself space, and stabilize the detection performances.
Anywhere, in the binary or real-valued space, the content incompleteness ina detector makes the detection effects unsatisfactory. To solve this problem, amulti-shape detection model with the immune network and immune dangertheory is proposed: the detection module of the system is divided into binarymodule and real-valued module, which complete collaborative detection bysignal mechanism. The experiments validate that the model adapts to the morecomplex events to be detected, and the detection effects can maintain a relativelystable level in different environments.
This paper studies primarily the optimization and the detection of thedetector in the immunity-based intrusion detection system, and proposescorresponding solutions for the existing problems. The above research contentsnot only provide some new methods to immunity-based intrusion detection, butalso broaden the scope of the study on artificial immune theory and itsapplications.
引文
[1] BOUKERCHE A, MACHADO R B, JUCA R L. An agent based and biologicalinspired real-time intrusion detection and security model for computer networkoperations [J]. Computer Communications,2007,30(13):2649-2660.
[2] DAL D, ABRAHAM S, ABRAHAM A and et al. Evolutionary inducedsecondary immunity: an artificial immune systems based intrusion detectionsystems [C]. In: Proceedings of the7th Computer Information Systems andIndustrial Management Applications, Ostrava, Czech Republic,2008:65-70.
[3] HART E, TIMMIS J. Application areas of AIS: the past, the present and thefuture [J]. Applied Soft Computing,2005,8(1):191-201.
[4] DASGUPTA D, YU S, NINO F. Recent Advances in Artificial Immune Systems:Models and Applications [J]. Applied Soft Computing,2011,11(2):1574-1587.
[5] DENIZ E, U¨LKER S. Clonal selection algorithm application to simplemicrowave matching network [J]. Microwave and Optical Technology Letters,2011,53(5):38-40.
[6] GHOSH K, SRINIVASAN R. Immune-system-inspired approach to processmonitoring and fault diagnosis [J]. Industrial and Engineering ChemistryResearch,2011,50(3):1637-1651.
[7] YANG H D, GUO J H, DENG F Q. Collaborative RFID intrusion detection withan artificial immune system [J]. Journal of Intelligent Information Systems,2011,36(1):1-26.
[8] BOWSHER C G. Information processing by biochemical networks: A dynamicapproach [J]. Journal of the Royal Society Interface,2011,8(55):186-200.
[9] WILSON W, BIRKIN P, AICKELIN U. Motif detection inspired by immunememory [J]. Journal of the Operational Research Society,2011,62(2):253-265.
[10] LI M, REN W X. Negative selection algorithm using natural frequency fornovelty detection under temperature variations [C]. In: Proceedings of2011International Conference on Structures and Building Materials, Guangzhou,China,2011:2747-2750.
[11] QIAO Y K, ZHANG Q, ZHANG J S. A fault predication algorithm based onartificial immune particle filter [C]. In: Proceedings of2010InternationalConference on Frontiers of Manufacturing and Design Science, Chongqing,China,2010:3459-3463.
[12] CHEN P, LI X, REN S B and et al. New immune algorithm and application inpower filter optimization design [C]. In: Proceedings of2011InternationalConference on Engineering Materials, Energy, Management and Control, Beijing,China,2011:555-560.
[13]丁建立,慈祥,黄剑雄.一种基于免疫遗传算法的网络新词识别方法[J].计算机科学,2011,38(1):240-244.
[14] ZHOU J, DASGUPTA D. V-detector: an efficient negative selection algorithmwith “probably adequate” detector coverage [J]. Information Science,2009,179(10):1390-1406.
[15] CASTRO P A, VON Z, FERNANDO J. A Gaussian artificial immune system formulti-objective optimization in continuous domains [C]. In: Proceedings of the10th International Conference on Hybrid Intelligent Systems, Atlanta, GA,United states,2010:159-164.
[16] DANZIGER M, DE L N. A hybrid approach for IEEE802.11intrusion detectionbased on AIS, MAS and na ve bayes [C]. In: Proceedings of the10thInternational Conference on Hybrid Intelligent Systems, Atlanta, GA, Unitedstates,2010:201-204.
[17] CECILIA S, KEITH W. Novelty detection in a changing environment: a negativeselection approach [J]. Mechanical Systems and Signal Processing,2010,24(4):1114-1128.
[18] MUNA E, AZWEEN A, BRAHIM B S. Immune multi agent system forintrusion prevention and self healing system implement a non-linearclassification [C]. In: Proceedings of2010International Symposium inInformation Technology, Kuala Lumpur, Malaysia,2010:1-6.
[19]杨义先,钮心忻.入侵检测理论与技术[M].高等教育出版社,北京,2006:47-56.
[20] ZHOU J, DASGUPTA D. Revisiting Negative Selection Algorithms [J].Evolutionary Computation,2007,15(2):223-251.
[21] DE CASTRO L N, VON ZUBEN F J. Artificial immune systems: part I-basictheory and applications [C/OL].1999:1-15[2012-03-17].http://eva.evannai.inf.uc3m.es/docencia/doctorado/cib/documentacion/OverviewIS.pdf.
[22] DASGUPTA D, FORREST S. Artificial immune systems in industrialapplications [C]. In: Proceedings of the2nd International Conference onIntelligent Processing and Manufacturing of Materials, Honolulu, USA,1999:257-267.
[23]莫宏伟.人工免疫网络记忆分类器原理与应用研究[D].哈尔滨:哈尔滨工程大学,2005:8-31.
[24] FORREST S, PERELSON A S, ALLEN L. Self-nonself discrimination in acomputer [C]. In: Proceedings of IEEE Society Symposium on Research inSecurity and Privacy and Privacy1994, Massachusetts, USA,1994:202-212.
[25] MENG Q H, ZHAO W L. Study on fault diagnosis algorithm based on artificialimmune danger theory [C]. In: Proceedings of2010International Conference onMechanic Automation and Control Engineering, Wuhan, China,2010:5997-6000.
[26]王慧.基于危险理论的网络入侵检测系统研究[J].计算机仿真,2010,27(6):159-162.
[27]耿强,王成良.免疫遗传蚁群融合算法[J].计算机工程与应用,2010,46(23):44-46.
[28]常志英,韩莉,姜大伟.改进的克隆选择算法及其应用[J].计算机工程,2011,37(1):173-174.
[29]王磊,王伟,李玉祥.基于人工免疫细胞模型的模糊聚类算法[J].计算机工程,2011,37(5):13-15.
[30]李红婵,朱颢东.并行自适应免疫量子粒子群优化算法[J].计算机工程,2011,37(5):221-223.
[31] GONZALEZ F, DASGUPTA D, KOZMA R. Combining negative selection andclassification technique for anomaly detection [C]. In: Proceedings of Congresson Evolutionary computation2002, Honolulu, HI, USA,2002:705-710.
[32] GREENSMITH J, TWYCROSS J, AICKELIN U. Dendritic cells for anomalydetection [C]. In: Proceedings of IEEE Congress on Evolutionary Computation2006, Vancouver, BC, Canada,2006:664-671.
[33] BARREIRA A F, TEIXEIRA O N, DE J G and et al. Evolutionary artificialimmune system optimization [C]. In: Proceedings of the12th Annual Geneticand Evolutionary Computation Conference, Portland, OR, United states,2010:2065-2066.
[34] LAURENTYS C A, PALHARES R M, CAMINHAS W M. A novel artificialimmune system for fault behavior detection [J]. Expert Systems withApplications,2011,38(6):6957-6966.
[35] DASGUPTA D, SAHA S. Password security through negative filtering [C]. In:Proceedings of2010International Conference on Emerging SecurityTechnologies, Canterbury, United Kingdom,2010:83-89.
[36] STIBOR T, TIMMIS J, ECKET C. Generalization regions in hamming negativeselection [C]. In: Proceedings of Intelligent Information and Web Mining2006,Ustron, Poland,2006:447-456.
[37] BALTHROP J, ESPONDA F, FORREST S and et al. Coverage andgeneralization in an artificial immune system [C]. In: Proceedings of the1stInternational Conference on Artificial Immune System2002, Canterbury, UK,2002:3-10.
[38] HARMER P K, WILLIAMS P O, GUNSCH G H. An artificial immune systemarchitecture for computer security applications [J]. IEEE Transactions onEvolutionary Computation,2002,6(3):252-280.
[39] STIBOR T, TIMMIS J, ECKET C. On permutation masks in hamming negativeselection [C]. In: Proceedings of International Conference on Artificial ImmuneSystem2006, Oeiras, Portugal,2006:122-135.
[40] ELBERFELD M, TEXTOR J. Negative selection algorithms on strings withefficient training and linear-time classification [J].Theoretical Computer Science,2011,412(6):534-542.
[41]杨东勇,陈晋因.基于多种群遗传算法的检测器生成算法研究[J].自动化学报,2009,35(4):425-432.
[42]蔡涛,鞠时光,仲魏等.基于切割的检测器生成算法[J].电子学报,2009,37(4A):131-134.
[43]蔡涛,鞠时光,牛德姣.快速否定选择算法的研究与分析[J].小型微型计算机系统,2009,30(6):1171-1174.
[44]刘星宝,蔡自兴.负选择算法中检测器快速生成策略[J].小型微型计算机系统,2009,30(7):1263-1267.
[45]刘星宝,蔡自兴.种子检测器刺激-应答变异算法研究[J].高技术通讯,2009,19(3):273-278.
[46]杨铭魁.改进的变长检测器产生算法[J].计算机工程,2010,36(15):174-175.
[47]唐俊,赵晓娟.一种用于入侵检测系统的可变r匹配算法[J].计算机应用研究,2010，27(2):745-747.
[48] YUAN H, LIU J Y. Intrusion detection based on immune dynamical matchingalgorithm [C]. In: Proceedings of2010International Conference on E-Businessand E-Government, Guangzhou, China,2010:1342-1345.
[49] LIU Z, XU S, LI J. Research on detector generating algorithm based on artificialimmune [C]. In: Proceedings of the2nd International Conference on MultimediaInformation Networking and Security, Nanjing, China,2010:452-455.
[50] AMARAL J L M, AMARAL J F M, MORIN D and et al. An immune faultdetection system with automatic detector generation by genetic algorithm [C]. In:Proceedings of the7th International Conference on Intelligence Systems Designand Applications, Rio de Janeiro, Brazil,2007:283-288.
[51] HU Z B, ZHOU J, Ma P. A novel anomaly detection algorithm based on real-valued negative selection [C]. In: Proceedings of the1st International Workshopon Knowledge Discovery and Data Mining, Adelaide, Australia,2008:499-502.
[52] YI Z X, M X D, ZHANG L and et al. A matrix negative selection algorithm foranomaly detection [C]. In: Proceedings of Evolutionary Computation2008,Hong Kong, China,2008:978-983.
[53] ZHU T Y, MA Z X, LIU S J and et al. Improved negative selection algorithmbased on bloom filter [C]. In: Proceedings of2009International Conference onE-Business and Information System Security, Wuhan, China,2009:31-35.
[54]陈喆,周雁舟,吕志国.一个自体变异免疫检测器生成算法[J].计算机科学,2010,37(3):133-137.
[55] ZHOU J, DASGUPTA D. Real-valued negative selection algorithm withvariable-sized detectors [C]. In: Proceedings of the2004Conference on Geneticand Evolutionary Computation, Seattle, New York, USA,2004:287-298.
[56] ZHOU J, DASGUPTA D. Estimating the detector coverage in a negativeselection algorithm [C]. In: Proceedings of the Conference on Genetic andEvolutionary Computation2005, Washington DC, USA,2005:281-288.
[57] ZHOU J. A boundary-aware negative selection algorithm [C]. In: Proceedings ofArtificial Intelligence and Soft Computation2005, Benidom, Spain,2005:12-14.
[58] ZHOU J, DASGUPTA D. Applicability issues of the real-valued negativeselection algorithms [C]. In: Proceedings of the Conference on Genetic andEvolutionary Computation2006, Seattle, Washington, USA,2006:111-118.
[59] BALACHANDRAN S, DASGUPTA D, NINO F and et al. A framework forevolving multi-shaped detectors in negative selection [C]. In: Proceedings ofIEEE Symposium on Foundations of Computational Intelligence2007, Honolulu,Hawaii, USA,2007:401-408.
[60] GUI M, DAS S, PAHWA A. Procreating V-Detectors for nonself recognition: anapplication to anomaly detection in power systems [C]. In: Proceedings of the9th Annual Conference on Genetic and Evolutionary Computation, London,England,2007:261-268.
[61] XU B, ZHUANG Y. Hybrid detector based negative selection algorithm [C]. In:Proceedings of the5th International Conference on Wireless CommunicationsNetworking and Mobile Computing, Beijing, China,2009:1-4.
[62] WU Z F, WANG T, ZHANG Q H and et al. Research on generating detectoralgorithm in fault detection [C]. In: Proceedings of the2nd InternationalConference on Software Engineering and Data Mining, Chengdu, China,2010:23-26.
[63] AMARAL J L M, AMARAL J F M, TANSCHEIT R. Real-valued NegativeSelection Algorithm with a Quasi-Monte Carlo Genetic Detector Generation [C].In: Proceedings of the6th International Conference on Artificial Immune System,Santos, Brazil,2007:156-167.
[64] LEE H M, MAO C H. A self-adaptive evolutionary negative selection approachfor home anomaly events detection [C]. In: Proceedings of Knowledge-BasedIntelligent Information and Engineering Systems2007, Vietri sul Mare, Italy,2007:325-332.
[65] CHMIELEWSKI A, WIERZCHON S T. Simple method of increasing thecoverage of nonself region for negative selection algorithms [C]. In: Proceedingsof the6th International Conference on Computation Information Systems andIndustrial Management Applications, Elk Poland,2007:155-160.
[66] HALAVATI R, SHOURAKI S B, HERAVI M J and et al. An artificial immunesystem with partially specified antibodies [C]. In: Proceedings of2007Geneticand Evolutionary Computation Conference, London, United kingdom,2010:57-62.
[67]方贤进,李龙澍,钱海.基于人工免疫的网络入侵检测中疫苗算子的作用研究[J].计算机科学,2010,37(1):239-242.
[68]王辉,毕晓君,于立君等.基于疫苗理论的变阈值免疫阴性选择算法[J].哈尔滨工程大学学报,2011,32(1):69-72.
[69] LIU F, GONG M G, MA J J and et al. Optimizing detector distribution in v-detector negative selection using a constrained multiobjective immune algorithm[C]. In: Proceedings of Congress on Evolutionary computation2010, Barcelona,Spain,2010:1-8.
[70] VIOLATO, R P, AZZOLINI A G and et al. Antibodies with adaptive radius asprototypes of high-dimensional datasets [C]. In: Proceedings of the9thInternational Conference on Artificial Immune Systems, Edinburgh, Unitedkingdom,2010:158-170.
[71] KOTOV, V D, VASILYEV V I. Artificial immune systems based intrusiondetection system [C]. In: Proceedings of the2nd International Conference onSecurity of Information and Networks, Famagusta, Cyprus,2009:207-212.
[72] YANG H, LIANG Y W, LI T and et al. A model of collaborative artificialimmune system [C]. In: Proceedings of the2nd International Asia Conference onInformatics in Control, Automation and Robotics2010, Wuhan, China,2010:101-104.
[73] ZHENG X F, FANG Y H. An AIS-based cloud security model [C]. In:Proceedings of2010International Conference on Intelligent Control andInformation Processing, Dalian, China,2010:153-158.
[74] MABU S, CHEN C, LU N N and et al. An intrusion-detection model based onfuzzy class-association-rule mining using genetic network programming [J].IEEE Transactions on Systems, Man and Cybernetics, Part C: Applications andReviews,2011,41(1):130-139.
[75] ZAITSEV S, SUBBOTIN S. Hypercell as a hybrid artificial immune systemmodel [C]. In: Proceedings of2010International Conference on ModernProblems of Radio Engineering, Lviv-Slavske, Ukraine,2010:297-298.
[76]黄学宇,魏娜,陶建锋.基于人工免疫聚类的异常检测算法[J].计算机工程,2010,36(1):166-169.
[77] SUN F X, HAN X C, WANG J H. An immune danger theory inspired model fornetwork security monitoring [C]. In: Proceedings of2010InternationalConference on Challenges in Environmental Science and Computer Engineering,Wuhan, China,2010:33-35.
[78]陈岳兵,冯超,张权,唐朝京.面向入侵检测的集成人工免疫系统[J].通信学报,2012,33(2):125-131.
[79]徐佳，张卫.人工免疫系统中的抗体生成与匹配算法[J].计算机工程，2010,36(9):181-183.
[80] LI R, LUO W B. Intrusion response model based on AIS [C]. In: Proceedings of2010International Forum on Information Technology and Applications,Kunming, China,2010:86-90.
[81]彭凌西,谢冬青,付颖芳,熊伟,沈玉利.基于危险理论的自动入侵响应系统模型[J].通信学报,2012,33(1):136-144.
[82] STIBOR T, TIMMIS J. Comments on real-valued negative selection vs. real-valued positive selection and one-Class SVM [C]. In: proceedings ofEvolutionary Computation2007. Singapore,2007:3727-3734.
[83] STIBOR T, TIMMIS J, Eckert C. On the Use of Hyperspheres in ArtificialImmune Systems as Antibody Recognition Regions [C]. In: Preceeding of5thInternational Conference on Artificial Immune Systems, LNCS4163,2006:215-228.
[84]张凤斌,席亮,王胜文. V-detector优化算法[J].高技术通讯,2012,22(5):449-454.
[85]席亮,张凤斌,王大伟.混合匹配规则的否定选择算法[J].哈尔滨理工大学,2009,14(5):52-55.
[86] VERLEYSEN M. Learning high-dimensional data [J]. Limitations and FutureTrends in Neural Computation,2003,186:141-162.
[87]何晓群.多元统计分析[M].中国人民大学出版社,北京,2004:153-157.
[88]王大伟.基于生物免疫的检测器分布策略研究[D].哈尔滨:哈尔滨理工大学,2008.57-58.
[89] TEW J, PHIPPS P, MANDEL T. The maintenance and regulation of the humanimmune response: persisting antigen and the role of follicular antigen-bindingdendrtic cells [C]. Immunological Review,1980,53:175-211.
[90] UCI M L R. Fisher’s Iris Data [DB/OL].[2009-12-23].http://archive.ics.uci.edu/ml/datasets/Iris.
[91] DASGUPTA, D, YU SENHUA, MAJUMDAR N S, et al. MILA-Multilevelimmune learning algorithm [C]. In: Proceedings of the2003Conference onGenetic and Evolutionary Computation, Chicago, UNA,2003:201-214.
[92] LINCOLN LABS. KDD Cup Data Set1999[DB/OL].(2007-06-26). http://kdd.ics.uci.edu/databases/kddcup99/kddcup99.html.
[93]刘国兴.基于协同进化的多目标优化算法研究[D].天津:天津大学,2008:28-34.
[94] MACKAY J C. Introduction to Monte Carlo methods [M]. Oak Ridge, USA:Oak Ridge National Laboratory,1995:23-39.
[95] LIU J.S. Monte Carlo Strategies in Scientific Computing [M]. Germany:Springer,2001:53-77.
[96] HUNT J, COOK D. Learning using an artificial immune system [J]. Journal ofNetwork and Computer Applieatiom: Special Issue on Intelligent SystemsDesign.1996,19:189-212.
[97]马晶.基于免疫机理的入侵检测模型[D].成都:西华大学,2009:27-32.
[98]王珺,刘希玉,王鑫.人工免疫系统及其模型分析[J].计算机技术与发展,2006,16(7):105-107.
[99]王珺.基于人工免疫模型的数据挖掘及其应用[D].济南:山东师范大学,2007:15-19.
[100]黄旭波.计算机免疫学基本原理的探讨[C].第15届全国计算机新科技与计算机继续教育学术会议,秦皇岛,2004:486-492.
[101] JERNE N K. Towards a network theory of the immune system [J]. AnnualImmunology,1974,125C:373-489.
[102] MATZINGER P. Tolerance danger and the extended family [J]. Annual Reviewof Immunology,1994,12:991-1045.
[103] MATZINGER P. The Danger Model: A Renewed Sense of Self [J]. Science,2002,296:301-305.
[104] AICKELIN U, BENTLEY P, Cayzer S, et al. Danger theory: the link betweenAIS and IDS [C]. In: proceedings of the2nd International Conference onArtificial Immune Systems,2003:147-155.
[105] BRETSCHER P. The two-signal model of lymphocyte activation twenty-oneyears later [J]. Immunology Today,1992,13:74-76.
[106] GREENSMITH J, AICKELIN U, TWYCROSS J． Detecting danger:Applying a novel immunological concept to intrusion detection systems [C]. In:Proceeding of the6th International Conference in Adaptive Computing inDesign and Manufacture, Bristol, UK,2004:1-3.
[107] AICKELIN U, CAYZER S. The danger theory and its application to artificialimmune systems [C]. In: proceedings of the1st International Conference onArtificial Immune Systems, Canterbury, UK,2002:141-148.