免疫入侵检测自体与检测器动态自适应机制研究
摘要
随着信息产业的飞速发展，网络与信息安全存在的问题也越来越多。作为一种积极主动的网络安全技术，入侵检测的研究越来越受到广大学者的重视。而生物免疫系统所具有的自适应性、鲁棒性和自组织性等优良特性，可以很好地应用于入侵检测技术。基于生物免疫机制的入侵检测技术已经成为当前的一个研究热点。其中的自体集合和检测器集合作为系统检测模块的重要组成部分，对于系统的检测性能有着极其重要的作用，需要深入研究。本文就以自体集合和检测器集合为研究对象，围绕自体筛选与更新、检测器集合优化、自体与检测器集合学习机制等问题展开研究。
作为训练生成检测器的重要基础，自体集合本身存在许多不足，特别是在实值空间，比如多分区、边界交叉、自体样本重叠等，他们会造成边界黑洞、生成代价过高等检测器问题。为了解决以上问题，借鉴模糊聚类方法和概率统计中的高斯理论，提出一种自体集合优化算法，通过计算自体样本间的亲和力，用模糊聚类算法分化自体集合，并在各个分区内利用高斯理论处理噪声和高重叠。通过实验验证，该算法可以有效地解决自体集合存在的问题，从而提高生成检测器的效率。
自体集合是由正常数据的经验值构成的。由于环境在随时间变化而变化，过去的正常数据可能已经不能反映当前的真实情况，从而影响检测器的训练生成效果。针对这一问题，借鉴免疫监督机制、免疫反馈原理等，提出一种自体集合实时更新算法，该算法包含多个处理模块、辅助集合来处理不同情况下的自体操作及协同实时更新，从而有效地保证自体集合实时有效地反映真实环境。通过实验验证，算法可以很好地实现预期的目标，为检测器的训练和生成打下一个坚实的基础。
以基于免疫机制的入侵检测中的检测器为研究对象，针对其在实值空间下的黑洞、检测器重叠等问题，借鉴生物免疫系统调节机制，提出一种检测器集合优化算法，通过比较检测器间的亲和力，判断检测器的优良程度，并利用子代替代效果较差的个体来改善检测器的分布性能。通过实验测试，经优化后的检测器集合对非自体空间的覆盖率有了显著提高，有效地提高了检测器的检测性能。
检测器集合的动态更新对系统的检测性能起着关键作用。受到生物免疫系统中自体与免疫细胞随环境和时间不断变化更新的启发，借鉴生物工程领域的疫苗技术，提出一种检测器集合自适应学习算法，设计多个检测器学习模块，从而使得检测器可以随环境的变化而不断地学习新知识，实现了进化过程的自适应。通过实验证实，该算法可以有效地使检测器集合时刻保持对环境的认识，保持良好的检测性能。
本文主要研究基于免疫机制的入侵检测系统中的自体集合与检测器集合这两个系统检测模块最重要的部件，针对其中存在的问题提出相应的优化算法，加入动态更新和自适应学习机制来改善系统检测性能。以上内容不仅对基于免疫机制的入侵检测技术有很大的应用价值，而且其中的算法也拓宽了人工免疫理论及其相应的研究领域的研究范围。
With the information industry developments, there are more and moreproblems of network and information security. As a network security technologywhich has the initiative character, the research of intrusion detection system isattacting more and more sights of researchers. Moreover, the advantages ofbiology immune system, such as, self-adaption, self-organziation, dynamics, andso on, are applicable to the intrusion detection system. Sothat, immunity-basedintrusion detection system has being became a research hotspot. The central parts:self and detector set play a major role in detection performance. For that reason,this paper focuses on self set and detector set and their update, optimizationmethods, learning mechanism, etc. in immunity-based intrusion detection system.
The self set in the immune-based intrusion detection system which is used totrain detectors has some defects, especially, in the real-valued shape space: multi-area, overlapping, noising sample, etc. which can cause some problems, such asthe boundary holes of detector set, the high cost of generating detectors, etc. Tosolve the problems, a self set optimization algorithm is proposed, which usesfuzzy clustering algorithm and Gaussian-distribution theory. The fuzzy clusteringdeals with multi-areas and the Gaussian-distribution deals with the overlappingand noising. Experimental results show that, the optimization algorithm can solvethe selves’ problems, increase the efficiency of detector generation effectively.
The self set is made up of the empirical data which can not mirror thecurrent real facts with the changing environments. This would lead to problemswith the detector generation. To solve the problems, borrowing ideas fromsupervisory mechanisms, immune feedback theory, etc. in biology immue system,a self set real-time update algorithm is proposed. This algorithm includes some modules and auxiliary sets which can deal with the different operations andupdate the self set collaboratively and let the selves keep pace with the changingenvironments. Experimental results show that, the algorithm can achieve theintended purpose, lay solid foundations for detector generation.
Detector set, the most important role in the immunity-based intrusiondetection system, also has some problems, especially, in the the real-valued shapespace. The holes and overlapping problems has not been solved effectively before.To solve these problems, an optimization algorithm for detectors is proposed,inspired by the immunoregulation of immune cells in biology immune system:Updating the detector set by the candidates generated from their parents and theaffinity comparison to improve detectors’ distribution performance. Theexperimental results show that the optimized detectors can increase the efficiencyof detectors’ distribution and improve the detection performance of detector set.
The detectors’ dynamic update impacts on the detection performances. Inthe biological immune system, the dynamics of self cells and immune cells is toensure the system adapt to the changing environments. And in the biomedicalengineering, the vaccine mechanism is an important role on fighting off the virusviolations. To deal with the detector problems, this paper proposes an adaptivelearning algorithm of detector set with standpoint of the vaccines and dynamicdetectors. It contains some detector learning modules and keeps the detector setlearning and adaptive adjusting with environment. Experiments results show that,the algorithm can let the detector set keep a real-time understanding on thechanging environment and keep the detection performances.
The researches on the self set and detector set which are the most importantroles in immunity-based intrusion detection system analyze the problems, mainlyfocus on the optimization algorithms, the dynamic update and adaptive learningalgorithms to increase the system’s detection performances. The contents areuseful for not only the immunity-based intrusion detection system, but also theartificial immune theory and its correlative research fields.
作为训练生成检测器的重要基础，自体集合本身存在许多不足，特别是在实值空间，比如多分区、边界交叉、自体样本重叠等，他们会造成边界黑洞、生成代价过高等检测器问题。为了解决以上问题，借鉴模糊聚类方法和概率统计中的高斯理论，提出一种自体集合优化算法，通过计算自体样本间的亲和力，用模糊聚类算法分化自体集合，并在各个分区内利用高斯理论处理噪声和高重叠。通过实验验证，该算法可以有效地解决自体集合存在的问题，从而提高生成检测器的效率。
自体集合是由正常数据的经验值构成的。由于环境在随时间变化而变化，过去的正常数据可能已经不能反映当前的真实情况，从而影响检测器的训练生成效果。针对这一问题，借鉴免疫监督机制、免疫反馈原理等，提出一种自体集合实时更新算法，该算法包含多个处理模块、辅助集合来处理不同情况下的自体操作及协同实时更新，从而有效地保证自体集合实时有效地反映真实环境。通过实验验证，算法可以很好地实现预期的目标，为检测器的训练和生成打下一个坚实的基础。
以基于免疫机制的入侵检测中的检测器为研究对象，针对其在实值空间下的黑洞、检测器重叠等问题，借鉴生物免疫系统调节机制，提出一种检测器集合优化算法，通过比较检测器间的亲和力，判断检测器的优良程度，并利用子代替代效果较差的个体来改善检测器的分布性能。通过实验测试，经优化后的检测器集合对非自体空间的覆盖率有了显著提高，有效地提高了检测器的检测性能。
检测器集合的动态更新对系统的检测性能起着关键作用。受到生物免疫系统中自体与免疫细胞随环境和时间不断变化更新的启发，借鉴生物工程领域的疫苗技术，提出一种检测器集合自适应学习算法，设计多个检测器学习模块，从而使得检测器可以随环境的变化而不断地学习新知识，实现了进化过程的自适应。通过实验证实，该算法可以有效地使检测器集合时刻保持对环境的认识，保持良好的检测性能。
本文主要研究基于免疫机制的入侵检测系统中的自体集合与检测器集合这两个系统检测模块最重要的部件，针对其中存在的问题提出相应的优化算法，加入动态更新和自适应学习机制来改善系统检测性能。以上内容不仅对基于免疫机制的入侵检测技术有很大的应用价值，而且其中的算法也拓宽了人工免疫理论及其相应的研究领域的研究范围。
With the information industry developments, there are more and moreproblems of network and information security. As a network security technologywhich has the initiative character, the research of intrusion detection system isattacting more and more sights of researchers. Moreover, the advantages ofbiology immune system, such as, self-adaption, self-organziation, dynamics, andso on, are applicable to the intrusion detection system. Sothat, immunity-basedintrusion detection system has being became a research hotspot. The central parts:self and detector set play a major role in detection performance. For that reason,this paper focuses on self set and detector set and their update, optimizationmethods, learning mechanism, etc. in immunity-based intrusion detection system.
The self set in the immune-based intrusion detection system which is used totrain detectors has some defects, especially, in the real-valued shape space: multi-area, overlapping, noising sample, etc. which can cause some problems, such asthe boundary holes of detector set, the high cost of generating detectors, etc. Tosolve the problems, a self set optimization algorithm is proposed, which usesfuzzy clustering algorithm and Gaussian-distribution theory. The fuzzy clusteringdeals with multi-areas and the Gaussian-distribution deals with the overlappingand noising. Experimental results show that, the optimization algorithm can solvethe selves’ problems, increase the efficiency of detector generation effectively.
The self set is made up of the empirical data which can not mirror thecurrent real facts with the changing environments. This would lead to problemswith the detector generation. To solve the problems, borrowing ideas fromsupervisory mechanisms, immune feedback theory, etc. in biology immue system,a self set real-time update algorithm is proposed. This algorithm includes some modules and auxiliary sets which can deal with the different operations andupdate the self set collaboratively and let the selves keep pace with the changingenvironments. Experimental results show that, the algorithm can achieve theintended purpose, lay solid foundations for detector generation.
Detector set, the most important role in the immunity-based intrusiondetection system, also has some problems, especially, in the the real-valued shapespace. The holes and overlapping problems has not been solved effectively before.To solve these problems, an optimization algorithm for detectors is proposed,inspired by the immunoregulation of immune cells in biology immune system:Updating the detector set by the candidates generated from their parents and theaffinity comparison to improve detectors’ distribution performance. Theexperimental results show that the optimized detectors can increase the efficiencyof detectors’ distribution and improve the detection performance of detector set.
The detectors’ dynamic update impacts on the detection performances. Inthe biological immune system, the dynamics of self cells and immune cells is toensure the system adapt to the changing environments. And in the biomedicalengineering, the vaccine mechanism is an important role on fighting off the virusviolations. To deal with the detector problems, this paper proposes an adaptivelearning algorithm of detector set with standpoint of the vaccines and dynamicdetectors. It contains some detector learning modules and keeps the detector setlearning and adaptive adjusting with environment. Experiments results show that,the algorithm can let the detector set keep a real-time understanding on thechanging environment and keep the detection performances.
The researches on the self set and detector set which are the most importantroles in immunity-based intrusion detection system analyze the problems, mainlyfocus on the optimization algorithms, the dynamic update and adaptive learningalgorithms to increase the system’s detection performances. The contents areuseful for not only the immunity-based intrusion detection system, but also theartificial immune theory and its correlative research fields.
引文
[1]穆成坡,黄厚宽,田盛丰等.自动入侵响应决策技术的研究综述[J].计算机研究与发展,2008,45(8):1290-1298.
[2]卿斯汉,蒋建春,马恒太等.入侵检测技术研究综述[J].通信学报,2004,25(7):19-29.
[3]岳兵,傅红娟,刘伯莹等.完善入侵检测系统审计信息的方法[J].计算机学报,2003,25(7):772-777.
[4] HART E, TIMMIS J. Application areas of AIS: the past, the present and thefuture [J]. Applied Soft Computing,2005,8(1):191-201.
[5] BRANCO P J C, DENTE J A. Using immunology principle for fault detection[J]. Industrial Electronics,2003,50(2):362-373.
[6] DENIZ E, U¨LKER S. Clonal selection algorithm application to simplemicrowave matching network [J]. Microwave and Optical Technology Letters,2011,53(5):38-40.
[7] WILSON W, BIRKIN P, AICKELIN U. Motif detection inspired by immunememory [J]. Journal of the Operational Research Society,2011,62(2):253-265.
[8] 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.
[9] 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.
[10]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.
[11]陈云芳,王如传.基于免疫算法的分类器设计[J].计算机科学,2008,35(2):133-136.
[12] BOWSHER C G. Information processing by biochemical networks: A dynamicapproach [J]. Journal of the Royal Society Interface,2011,8(55):186-200.
[13] GHOSH K, SRINIVASAN R. Immune-system-inspired approach to processmonitoring and fault diagnosis [J]. Industrial and Engineering ChemistryResearch,2011,50(3):1637-1651.
[14] 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.
[15] CECILIA S, KEITH W. Novelty detection in a changing environment: anegative selection approach [J]. Mechanical Systems and Signal Processing,2010,24(4):1114-1128.
[16] 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.
[17] CASTRO P A, VON Z, FERNANDO J. A Gaussian artificial immune systemfor multi-objective optimization in continuous domains[C]. In: Proceedings ofthe10th International Conference on Hybrid Intelligent Systems, Atlanta, GA,United states,2010:159-164.
[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] KIM J，BENTLEY P．The Human Immune System and Network IntrusionDetection[C]． In: Proceedings of7th European Congress on IntelligentTechniques Soft Computing, Aachan, Germany,1999:1244-1250.
[21]李涛.基于免疫的网络监控模型[J].计算机学报,2006,2(9):1515-1522.
[22] ZHOU J, DASGUPTA D. Revisiting Negative Selection Algorithms [J].Evolutionary Computation,2007,15(2):223-251.
[23] TEW J, PHIPPS P, MANDEL T. The maintenance and regulation of the humanimmune response: persisting antigen and the role of follicular antigen-bindingdendrtic cells [J]. Immunological Review,1980,53:175-211.
[24] TAKAHASHI K, YAMADA T. Application of an immune feedback mechanismto control systems [J]. JSME International Journal Series C,1998,41(2):184-191.
[25] ISHIGURO A, KONDO T, WATANABE Y, et al. Dynamic behavior arbitrationof autonomous mobile robots using immune networks [C]. In: Proceedings of1995IEEE International Conference on Evolutionary Computation, Perth,Australia,1995,2:722-727.
[26]焦李成,杜海峰.人工免疫系统进展与展望[J].电子学报,2003,31(10):1540-1547.
[27] FORREST S, PERELSON A S, ALLEN L. Self-nonself discrimination in acomputer [C]. In: Proceedings of1994IEEE Society Symposium on Researchin Security and Privacy and Privacy, Massachusetts, USA,1994:202-212.
[28] GONZALEZ F, DASGUPTA D, KOZMA R. Combining negative selection andclassification technique for anomaly detection [C]. In: Proceedings of2002Congress on Evolutionary computation, Honolulu, HI, USA,2002:705-710.
[29] CASTRO N, TIMMIS J. Artificial Immune System: A new ComputationalIntelligence Approach [M]. Berlin: Springer,2002:23-50.
[30] KIM J, BENTLEY P J. An Evaluating Negative Selection in an ArtificialImmune System for Network Intrusion Detection [C]. In: Proceedings of2001Genetic and Evolutionary Computation Conference, San Francisco, USA,2001:1330-1337.
[31] GREENSMITH J, TWYCROSS J, AICKELIN U. Dendritic cells for anomalydetection. In: Proceedings of2006IEEE Congress on EvolutionaryComputation, Vancouver, BC, Canada,2006:664-671.
[32] STIBOR T, TIMMIS J, ECKET C. On the appropriateness of negative selectiondefined over hamming shape-space as a network intrusion detection system [C].In: Proceedings of2005IEEE Congress on Evolutionary Computation,Edinburgh, UK,2005:995-1002.
[33] STIBOR T, TIMMIS J, ECKET C. The link between r-contiguous detectors andk-cnf satisfactory [C]. In: Proceedings of2006IEEE Congress on EvolutionaryComputation, Vancouver, BC, Canada,2006:16-21.
[34] STIBOR T, TIMMIS J, ECKET C. Generalization regions in hamming negativeselection [C]. In: Proceedings of2006International Conference on IntelligentInformation and Web Mining. Ustron, Poland,2006:447-456.
[35] BALTHROP J, ESPONDA F, FORREST S and et al. Coverage andgeneralization in an artificial immune system [C]. In: Proceedings of firstInternational Conference on Artificial Immune System, Canterbury, UK,2002:3-10.
[36] 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.
[37] STIBOR T, TIMMIS J, ECKET C. On permutation masks in hamming negativeselection [C]. In: Proceedings of2006International Conference on ArtificialImmune System, Oeiras, Portugal,2006:122-135.
[38] ELBERFELD M, TEXTOR J. Negative selection algorithms on strings withefficient training and linear-time classification [J]. Theoretical ComputerScience,2011,412(6):534-542.
[39] GONZALEZ F, DASGUPTA D, KOZMA R. Combining negative selection andclassification technique for anomaly detection [C]. In: proceedings of2002Congress on Evolutionary computation, Honolulu, HI, USA,2002:705-710.
[40] GONZALEZ F, DASGUPTA D. Anomaly detection using real-valued negativeselection [J]. Journal of Genetic Programming and Evolvable Machines,2003,4(4):383-403.
[41] GAO X Z, OVASKA S J, WANG X. Genetic algorithm based detectorgeneration in negative selection algorithm [C]. In: Proceedings of2006International Conference on Adaptive and Learning Systems, Logan, USA,2006:133-137.
[42] 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 SystemsDesign and Applications, Rio de Janeiro, Brazil,2007:283-288.
[43] HU ZHENGBIN, ZHOU JI, MA PING. A novel anomaly detection algorithmbased on real-valued negative selection [C]. In: Proceedings of FirstInternational Workshop on Knowledge Discovery and Data Mining, Adelaide,Australia,2008:499-502.
[44] ZHOU J, DASGUPTA D. Real-valued negative selection algorithm withvariable-sized detectors. In: Proceedings of2004Conference on Genetic andEvolutionary Computation, Seattle, New York, USA,2004:287-298.
[45] ZHOU J, DASGUPTA D. Estimating the detector coverage in a negativeselection algorithm. In: Proceedings of the2005Conference on Genetic andEvolutionary Computation, Washington DC, USA,2005:281-288.
[46] ZHOU J. A boundary-aware negative selection algorithm [C]. In: Proceedings of2005International Conference on Artificial Intelligence and Soft Computation,Benidom, Spain,2005:12-14.
[47] ZHOU J, DASGUPTA D. V-Detector: An Efficient Negative SelectionAlgorithm with “Probably Adequate” Detector Coverage [J]. InformationScience,2009,179(10):1390-1406.
[48] BALACHANDRAN S, DASGUPTA D, NINO F and et al. A framework forevolving multi-shaped detectors in negative selection [C]. In: Proceedings of2007IEEE Symposium on Foundations of Computational Intelligence,Honolulu, Hawaii, USA,2007:401-408.
[49] 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.
[50] 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 of6th International Conference on Artificial Immune System,Santos, Brazil,2007:156-167.
[51] LEE H M, MAO C H. A self-adaptive evolutionary negative selection approachfor home anomaly events detection [C]. In: Proceedings of2007InternationalConference on Knowledge-Based Intelligent Information and EngineeringSystems, Vietri sul Mare, Italy,2007:325-332.
[52] CHMIELEWSKI A, WIERZCHON S T. V-Detector algorithm with tree-basedstructures [C]. In: Proceedings of the2006International Multiconference onComputer Science and Information Technology, Wisla Poland,2006:11-16.
[53] ADADEH M S, HABIBI J, DANESHI M and et al. Intrusion detection using ahybrid-ization of evolutionary fuzzy systems and artificial immune systems [C].In: Proceedings of2007International Conference on Evolutionary Computation.Singapore,2007:3547-3553.
[54] POWERS S T, HE JIE. A hybrid artificial immune system and self organizingmap for network intrusion detection [J]. Information Science,2008,178(5):3024-3042.
[55] FANELLI R L. A hybrid model for immune inspired network intrusion detection[C]. In: Proceedings of the7th International Conference on Artificial ImmuneSystems, Phuket, Thailand,2008:107-118.
[56] KATJA L, RAINER B, TANSU A and et al. A cooperative AIS framework forintrusion detection [C]. In: Proceedings of2007IEEE International Conferenceon Communications, Glasgow, Scotland,2007:1409-1416.
[57] HAAG C R, LAMONT G B, WILLIAMS P D and et al. An artificial immunesystem-inspired multiobjective evolutionary algorithm with application to thedetection of distributed computer network intrusions [C]. In: Proceedings of the6th International Conference on Artificial Immune Systems, Santos, Brazil,2007:2717-2724.
[58] CHMIELEWSKI A, WIERZCHON S T. Simple method of increasing thecoverage of nonself region for negative selection algorithms [C]. In:Proceedings of the6th International Conference on Computation InformationSystems and Industrial Management Applications, Elk Poland,2007:155-160.
[59] 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.
[60] 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.
[61] 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.
[62] GUI M, DAS S, PAHWA A. Procreating V-detectors for nonself recognition: anapplication to anomaly detection in power systems [C]. In: Proceedings of2007Genetic and Evolutionary Computation Conference, London, United Kingdom,2007:261-268.
[63] 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.
[64] 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.
[65] 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.
[66] 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.
[67]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.
[68]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.
[69]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.
[70]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.
[71]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.
[72]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.
[73]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.
[74]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.
[75]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.
[76]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.
[77]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.
[78]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.
[79] 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.
[80] 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.
[81] 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.
[82] YI Z X, M X D, ZHANG L and et al. A matrix negative selection algorithm foranomaly detection [C]. In: Proceedings of2008International Conference onEvolutionary Computation, Hong Kong, China,2008:978-983.
[83] 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.
[84]朱思峰,刘芳,柴争义.基于检测器覆盖率评估的否定选择算法[J].华中科技大学学报(自然科学版),2010,37(1):36-40.
[85]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.
[86] 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.
[87]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.
[88] LIU F, GONG M G, MA J J and et al. Optimizing detector distribution in v-detector negative selection using a constrained multiobjective immunealgorithm [C]. In: Proceedings of2010Congress on Evolutionary computation,Barcelona, Spain,2010:1-8.
[89]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.
[90]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.
[91]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.
[92] YANG H, LIANG Y W, LI T and et al. A model of collaborative artificialimmune system [C]. In: Proceedings of the2nd International Asia Conferenceon Informatics in Control, Automation and Robotics, Wuhan, China,2010:101-104.
[93] 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.
[94] 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.
[95] 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.
[96] STIBOR T, TIMMIS J, ECKERT C. A comparative study of real-valuednegative selection to statistical anomaly detection techniques [C]. In:Proceedings of4th International Conference on Artificial Immune Systems,Banff, Alta, Canada,2005:262-275.
[97] STIBOR T, TIMMIS J. Commnets on real-valed negative selection vs. real-valued positive selection and one-Class SVM [C]. In: Proceedings of2007International Conference on Evolutionary Computation, Singapore,2007:3727-3734.
[98] LINCOLN LABS. KDD Cup Data Set1999[DB/OL].(2007-06-26). http://kdd.ics.uci.edu/databases/kddcup99/kddcup99.html.
[99]孙吉贵,刘杰,赵连宇.聚类算法研究[J].软件学报,2008,19(1):48-61.
[100] SHENG W, LIU X. A Genetic K-medoids Clustering Algorithm[J]. Journal ofHeuristies,2006,12(6):447-466.
[101]蔡伟鸿,刘震.基于密度聚类算法的入侵检测研究[J].计算机工程与应用,2005,41(21):149-151.
[102] BEZDEK J C. Pattern Recognition with Fuzzy Objective Function Algorithms[M]. New York: Plenum press,1981:101-125.
[103] WILKIN G A, HUANG X. K-means Clustering Algorithms: Implementationand Comparison [C]. In: Proceedings of the2nd International Multi-SymPosiums on Computer and Computational Science, Iowa, USA,2007:133-136.
[104]向继,高能,荆继武.聚类算法在网络入侵检测中的应用[J].计算机工程,2003,29(16):48-50.
[105] JORMA K, ILKKA N. Testing the Gaussian Approximation of AggregateTraffic [C]. In: Proceedings of2nd Internet Measurement Workshop, Marseille,France,2002:49-61.
[106] BEZDEK J C. A Convergence Theorem for the Fuzzy ISODATA ClusteringAlgorithms [J]. IEEE Transactions on Pattern Analysis and MachineIntelligence,1980, PAMI-2(1):1-8.
[107] BEZDEK J C, HATHAWAY R J, HOWARD R E, and et al. LocalConvergence Analysis of a Grouped Variable Version of Coordinate Descent [J].Journal of Optimization Theory and Applications,1987,54(3):471-477.
[108] UCI MACHINE LEARNING REPOSITORY. Fisher’s Iris Data [DB/OL].(2009-12-23), http://archive.ics.uci.edu/ml/datasets/Iris.
[109]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.
[110] LI G Y, LI T, ZENG J, and et al. An improved v-detector algorithm ofidentifying boundary[C]. In: Proceedings of the8th International Conference onMachine Learning and Cybernetics, Baoding, China,2009:3209-3214.
[111] LI G Y, LI T, ZENG J, and et al. Negative selection algorithm based onimmune suppression[C]. In: Proceedings of the8th International Conference onMachine Learning and Cybernetics, Baoding, China,2009:3227-3232.
[112] ZHANG Q H, FU Y Z, XU B G. A new model of self-adaptive networkintrusion detection[C]. In: Proceedings of2008IEEE World Congress onComputational Intelligence, Hong Kong,2008:436–439.
[113] LIU F, GONG M G, MA J J, and et al. Optimizing detector distribution in v-detector negative selection using a constrained multiobjective immunealgorithm [C].//In: Proceedings of2010Congress on Evolutionary computation,Barcelona, Spain,2010:1-8.
[114] MACKAY J C. Introduction to Monte Carlo methods [M]. Oak Ridge NationalLaboratory, Oak Ridge, USA,1995:23-39.
[115] LIU J.S. Monte Carlo Strategies in Scientific Cumputing [M]. Springer-Verleg,Berlin, Germany,2001:53-77.
[116]洪征,吴礼发,王元元.应用改进的V-detector算法检测蠕虫[J].北京邮电大学学报,2007,30(2):98-101.
[2]卿斯汉,蒋建春,马恒太等.入侵检测技术研究综述[J].通信学报,2004,25(7):19-29.
[3]岳兵,傅红娟,刘伯莹等.完善入侵检测系统审计信息的方法[J].计算机学报,2003,25(7):772-777.
[4] HART E, TIMMIS J. Application areas of AIS: the past, the present and thefuture [J]. Applied Soft Computing,2005,8(1):191-201.
[5] BRANCO P J C, DENTE J A. Using immunology principle for fault detection[J]. Industrial Electronics,2003,50(2):362-373.
[6] DENIZ E, U¨LKER S. Clonal selection algorithm application to simplemicrowave matching network [J]. Microwave and Optical Technology Letters,2011,53(5):38-40.
[7] WILSON W, BIRKIN P, AICKELIN U. Motif detection inspired by immunememory [J]. Journal of the Operational Research Society,2011,62(2):253-265.
[8] 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.
[9] 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.
[10]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.
[11]陈云芳,王如传.基于免疫算法的分类器设计[J].计算机科学,2008,35(2):133-136.
[12] BOWSHER C G. Information processing by biochemical networks: A dynamicapproach [J]. Journal of the Royal Society Interface,2011,8(55):186-200.
[13] GHOSH K, SRINIVASAN R. Immune-system-inspired approach to processmonitoring and fault diagnosis [J]. Industrial and Engineering ChemistryResearch,2011,50(3):1637-1651.
[14] 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.
[15] CECILIA S, KEITH W. Novelty detection in a changing environment: anegative selection approach [J]. Mechanical Systems and Signal Processing,2010,24(4):1114-1128.
[16] 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.
[17] CASTRO P A, VON Z, FERNANDO J. A Gaussian artificial immune systemfor multi-objective optimization in continuous domains[C]. In: Proceedings ofthe10th International Conference on Hybrid Intelligent Systems, Atlanta, GA,United states,2010:159-164.
[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] KIM J，BENTLEY P．The Human Immune System and Network IntrusionDetection[C]． In: Proceedings of7th European Congress on IntelligentTechniques Soft Computing, Aachan, Germany,1999:1244-1250.
[21]李涛.基于免疫的网络监控模型[J].计算机学报,2006,2(9):1515-1522.
[22] ZHOU J, DASGUPTA D. Revisiting Negative Selection Algorithms [J].Evolutionary Computation,2007,15(2):223-251.
[23] TEW J, PHIPPS P, MANDEL T. The maintenance and regulation of the humanimmune response: persisting antigen and the role of follicular antigen-bindingdendrtic cells [J]. Immunological Review,1980,53:175-211.
[24] TAKAHASHI K, YAMADA T. Application of an immune feedback mechanismto control systems [J]. JSME International Journal Series C,1998,41(2):184-191.
[25] ISHIGURO A, KONDO T, WATANABE Y, et al. Dynamic behavior arbitrationof autonomous mobile robots using immune networks [C]. In: Proceedings of1995IEEE International Conference on Evolutionary Computation, Perth,Australia,1995,2:722-727.
[26]焦李成,杜海峰.人工免疫系统进展与展望[J].电子学报,2003,31(10):1540-1547.
[27] FORREST S, PERELSON A S, ALLEN L. Self-nonself discrimination in acomputer [C]. In: Proceedings of1994IEEE Society Symposium on Researchin Security and Privacy and Privacy, Massachusetts, USA,1994:202-212.
[28] GONZALEZ F, DASGUPTA D, KOZMA R. Combining negative selection andclassification technique for anomaly detection [C]. In: Proceedings of2002Congress on Evolutionary computation, Honolulu, HI, USA,2002:705-710.
[29] CASTRO N, TIMMIS J. Artificial Immune System: A new ComputationalIntelligence Approach [M]. Berlin: Springer,2002:23-50.
[30] KIM J, BENTLEY P J. An Evaluating Negative Selection in an ArtificialImmune System for Network Intrusion Detection [C]. In: Proceedings of2001Genetic and Evolutionary Computation Conference, San Francisco, USA,2001:1330-1337.
[31] GREENSMITH J, TWYCROSS J, AICKELIN U. Dendritic cells for anomalydetection. In: Proceedings of2006IEEE Congress on EvolutionaryComputation, Vancouver, BC, Canada,2006:664-671.
[32] STIBOR T, TIMMIS J, ECKET C. On the appropriateness of negative selectiondefined over hamming shape-space as a network intrusion detection system [C].In: Proceedings of2005IEEE Congress on Evolutionary Computation,Edinburgh, UK,2005:995-1002.
[33] STIBOR T, TIMMIS J, ECKET C. The link between r-contiguous detectors andk-cnf satisfactory [C]. In: Proceedings of2006IEEE Congress on EvolutionaryComputation, Vancouver, BC, Canada,2006:16-21.
[34] STIBOR T, TIMMIS J, ECKET C. Generalization regions in hamming negativeselection [C]. In: Proceedings of2006International Conference on IntelligentInformation and Web Mining. Ustron, Poland,2006:447-456.
[35] BALTHROP J, ESPONDA F, FORREST S and et al. Coverage andgeneralization in an artificial immune system [C]. In: Proceedings of firstInternational Conference on Artificial Immune System, Canterbury, UK,2002:3-10.
[36] 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.
[37] STIBOR T, TIMMIS J, ECKET C. On permutation masks in hamming negativeselection [C]. In: Proceedings of2006International Conference on ArtificialImmune System, Oeiras, Portugal,2006:122-135.
[38] ELBERFELD M, TEXTOR J. Negative selection algorithms on strings withefficient training and linear-time classification [J]. Theoretical ComputerScience,2011,412(6):534-542.
[39] GONZALEZ F, DASGUPTA D, KOZMA R. Combining negative selection andclassification technique for anomaly detection [C]. In: proceedings of2002Congress on Evolutionary computation, Honolulu, HI, USA,2002:705-710.
[40] GONZALEZ F, DASGUPTA D. Anomaly detection using real-valued negativeselection [J]. Journal of Genetic Programming and Evolvable Machines,2003,4(4):383-403.
[41] GAO X Z, OVASKA S J, WANG X. Genetic algorithm based detectorgeneration in negative selection algorithm [C]. In: Proceedings of2006International Conference on Adaptive and Learning Systems, Logan, USA,2006:133-137.
[42] 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 SystemsDesign and Applications, Rio de Janeiro, Brazil,2007:283-288.
[43] HU ZHENGBIN, ZHOU JI, MA PING. A novel anomaly detection algorithmbased on real-valued negative selection [C]. In: Proceedings of FirstInternational Workshop on Knowledge Discovery and Data Mining, Adelaide,Australia,2008:499-502.
[44] ZHOU J, DASGUPTA D. Real-valued negative selection algorithm withvariable-sized detectors. In: Proceedings of2004Conference on Genetic andEvolutionary Computation, Seattle, New York, USA,2004:287-298.
[45] ZHOU J, DASGUPTA D. Estimating the detector coverage in a negativeselection algorithm. In: Proceedings of the2005Conference on Genetic andEvolutionary Computation, Washington DC, USA,2005:281-288.
[46] ZHOU J. A boundary-aware negative selection algorithm [C]. In: Proceedings of2005International Conference on Artificial Intelligence and Soft Computation,Benidom, Spain,2005:12-14.
[47] ZHOU J, DASGUPTA D. V-Detector: An Efficient Negative SelectionAlgorithm with “Probably Adequate” Detector Coverage [J]. InformationScience,2009,179(10):1390-1406.
[48] BALACHANDRAN S, DASGUPTA D, NINO F and et al. A framework forevolving multi-shaped detectors in negative selection [C]. In: Proceedings of2007IEEE Symposium on Foundations of Computational Intelligence,Honolulu, Hawaii, USA,2007:401-408.
[49] 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.
[50] 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 of6th International Conference on Artificial Immune System,Santos, Brazil,2007:156-167.
[51] LEE H M, MAO C H. A self-adaptive evolutionary negative selection approachfor home anomaly events detection [C]. In: Proceedings of2007InternationalConference on Knowledge-Based Intelligent Information and EngineeringSystems, Vietri sul Mare, Italy,2007:325-332.
[52] CHMIELEWSKI A, WIERZCHON S T. V-Detector algorithm with tree-basedstructures [C]. In: Proceedings of the2006International Multiconference onComputer Science and Information Technology, Wisla Poland,2006:11-16.
[53] ADADEH M S, HABIBI J, DANESHI M and et al. Intrusion detection using ahybrid-ization of evolutionary fuzzy systems and artificial immune systems [C].In: Proceedings of2007International Conference on Evolutionary Computation.Singapore,2007:3547-3553.
[54] POWERS S T, HE JIE. A hybrid artificial immune system and self organizingmap for network intrusion detection [J]. Information Science,2008,178(5):3024-3042.
[55] FANELLI R L. A hybrid model for immune inspired network intrusion detection[C]. In: Proceedings of the7th International Conference on Artificial ImmuneSystems, Phuket, Thailand,2008:107-118.
[56] KATJA L, RAINER B, TANSU A and et al. A cooperative AIS framework forintrusion detection [C]. In: Proceedings of2007IEEE International Conferenceon Communications, Glasgow, Scotland,2007:1409-1416.
[57] HAAG C R, LAMONT G B, WILLIAMS P D and et al. An artificial immunesystem-inspired multiobjective evolutionary algorithm with application to thedetection of distributed computer network intrusions [C]. In: Proceedings of the6th International Conference on Artificial Immune Systems, Santos, Brazil,2007:2717-2724.
[58] CHMIELEWSKI A, WIERZCHON S T. Simple method of increasing thecoverage of nonself region for negative selection algorithms [C]. In:Proceedings of the6th International Conference on Computation InformationSystems and Industrial Management Applications, Elk Poland,2007:155-160.
[59] 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.
[60] 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.
[61] 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.
[62] GUI M, DAS S, PAHWA A. Procreating V-detectors for nonself recognition: anapplication to anomaly detection in power systems [C]. In: Proceedings of2007Genetic and Evolutionary Computation Conference, London, United Kingdom,2007:261-268.
[63] 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.
[64] 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.
[65] 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.
[66] 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.
[67]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.
[68]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.
[69]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.
[70]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.
[71]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.
[72]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.
[73]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.
[74]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.
[75]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.
[76]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.
[77]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.
[78]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.
[79] 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.
[80] 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.
[81] 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.
[82] YI Z X, M X D, ZHANG L and et al. A matrix negative selection algorithm foranomaly detection [C]. In: Proceedings of2008International Conference onEvolutionary Computation, Hong Kong, China,2008:978-983.
[83] 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.
[84]朱思峰,刘芳,柴争义.基于检测器覆盖率评估的否定选择算法[J].华中科技大学学报(自然科学版),2010,37(1):36-40.
[85]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.
[86] 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.
[87]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.
[88] LIU F, GONG M G, MA J J and et al. Optimizing detector distribution in v-detector negative selection using a constrained multiobjective immunealgorithm [C]. In: Proceedings of2010Congress on Evolutionary computation,Barcelona, Spain,2010:1-8.
[89]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.
[90]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.
[91]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.
[92] YANG H, LIANG Y W, LI T and et al. A model of collaborative artificialimmune system [C]. In: Proceedings of the2nd International Asia Conferenceon Informatics in Control, Automation and Robotics, Wuhan, China,2010:101-104.
[93] 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.
[94] 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.
[95] 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.
[96] STIBOR T, TIMMIS J, ECKERT C. A comparative study of real-valuednegative selection to statistical anomaly detection techniques [C]. In:Proceedings of4th International Conference on Artificial Immune Systems,Banff, Alta, Canada,2005:262-275.
[97] STIBOR T, TIMMIS J. Commnets on real-valed negative selection vs. real-valued positive selection and one-Class SVM [C]. In: Proceedings of2007International Conference on Evolutionary Computation, Singapore,2007:3727-3734.
[98] LINCOLN LABS. KDD Cup Data Set1999[DB/OL].(2007-06-26). http://kdd.ics.uci.edu/databases/kddcup99/kddcup99.html.
[99]孙吉贵,刘杰,赵连宇.聚类算法研究[J].软件学报,2008,19(1):48-61.
[100] SHENG W, LIU X. A Genetic K-medoids Clustering Algorithm[J]. Journal ofHeuristies,2006,12(6):447-466.
[101]蔡伟鸿,刘震.基于密度聚类算法的入侵检测研究[J].计算机工程与应用,2005,41(21):149-151.
[102] BEZDEK J C. Pattern Recognition with Fuzzy Objective Function Algorithms[M]. New York: Plenum press,1981:101-125.
[103] WILKIN G A, HUANG X. K-means Clustering Algorithms: Implementationand Comparison [C]. In: Proceedings of the2nd International Multi-SymPosiums on Computer and Computational Science, Iowa, USA,2007:133-136.
[104]向继,高能,荆继武.聚类算法在网络入侵检测中的应用[J].计算机工程,2003,29(16):48-50.
[105] JORMA K, ILKKA N. Testing the Gaussian Approximation of AggregateTraffic [C]. In: Proceedings of2nd Internet Measurement Workshop, Marseille,France,2002:49-61.
[106] BEZDEK J C. A Convergence Theorem for the Fuzzy ISODATA ClusteringAlgorithms [J]. IEEE Transactions on Pattern Analysis and MachineIntelligence,1980, PAMI-2(1):1-8.
[107] BEZDEK J C, HATHAWAY R J, HOWARD R E, and et al. LocalConvergence Analysis of a Grouped Variable Version of Coordinate Descent [J].Journal of Optimization Theory and Applications,1987,54(3):471-477.
[108] UCI MACHINE LEARNING REPOSITORY. Fisher’s Iris Data [DB/OL].(2009-12-23), http://archive.ics.uci.edu/ml/datasets/Iris.
[109]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.
[110] LI G Y, LI T, ZENG J, and et al. An improved v-detector algorithm ofidentifying boundary[C]. In: Proceedings of the8th International Conference onMachine Learning and Cybernetics, Baoding, China,2009:3209-3214.
[111] LI G Y, LI T, ZENG J, and et al. Negative selection algorithm based onimmune suppression[C]. In: Proceedings of the8th International Conference onMachine Learning and Cybernetics, Baoding, China,2009:3227-3232.
[112] ZHANG Q H, FU Y Z, XU B G. A new model of self-adaptive networkintrusion detection[C]. In: Proceedings of2008IEEE World Congress onComputational Intelligence, Hong Kong,2008:436–439.
[113] LIU F, GONG M G, MA J J, and et al. Optimizing detector distribution in v-detector negative selection using a constrained multiobjective immunealgorithm [C].//In: Proceedings of2010Congress on Evolutionary computation,Barcelona, Spain,2010:1-8.
[114] MACKAY J C. Introduction to Monte Carlo methods [M]. Oak Ridge NationalLaboratory, Oak Ridge, USA,1995:23-39.
[115] LIU J.S. Monte Carlo Strategies in Scientific Cumputing [M]. Springer-Verleg,Berlin, Germany,2001:53-77.
[116]洪征,吴礼发,王元元.应用改进的V-detector算法检测蠕虫[J].北京邮电大学学报,2007,30(2):98-101.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |