【作者】 刘振；

【导师】 徐苏；

【作者基本信息】 南昌大学 ， 计算机应用技术， 2010， 硕士

【摘要】 受生物免疫系统启发,模拟生物免疫系统原理、功能和模型的人工免疫为人们解决复杂的问题,提供了一种新的思路和方法。由于入侵检测系统的原理和生物免疫系统的原理在本质上的相似性,因此基于人工免疫的入侵检测系统成为计算机安全领域的一个新的研究热点。基于人工免疫的入侵检测系统通过产生相对有限的检测器来检测相对无限的入侵,所以检测器的产生是基于人工免疫的入侵检测系统的核心,检测器性能的好坏严重影响入侵检测系统检测能力的大小。本文紧紧围绕检测器的生成这一核心问题进行了广泛深入的研究。首先,在对入侵检测系统的作用、发展历程、实现技术和存在问题等方面进行简明而深入的综述后,对其发展趋势进行了展望；在介绍生物免疫系统的原理、层次结构和组成的基础上,分析了人工免疫中常用的算法。其次,通过对否定选择算法研究和分析,指出了算法存在的问题,针对这个问题对算法进行了改进；为了提高检测器的性能,能够检测未知的入侵,采用基于小生境的克隆选择算法对检测器进行进化；在分析漏洞产生原因的基础上,提出了一种快速计算漏洞的算法,探讨了漏洞个数与自体集个数之间的关系和漏洞个数与匹配阈值之间关系。最后,对改进的算法进行了仿真实验,通过理论分析和实验数据说明了改进算法的有效性。更多还原

【Abstract】 Inspired by the biologic immune system, modeling of biological immune system principle, function and the model of artificial immune, providing a new thinking and method for people to solve complex problems. Because of the similarity between the intrusion detection system and biological immune system, apply artificial immune to intrusion detection system as the research becomes the focus in the field of computer security.Based on artificial immune, intrusion detection system through the detector to produce relatively unlimited intrusion detection, therefore it is based on the detector artificial immune intrusion detection system, the core of the detector will have a direct impact on the detection performance of intrusion detection system. This paper is centering on the generating of detector for a more in-depth study.First, in the brief review of the intrusion detection system, development, technology and the problems existing in the of its development trend, Then introduce biological immune system principle, structure and composition, on the basis of the analysis of the artificial immune algorithm.Secondly, through to the negative selection algorithm analysis and study, points out the existing problems as well as the solution to the problem of the algorithm. In order to improve the performance of the detector, adopt the clonal selection algorithm based on niche for detector evolution; On the analysis of the causes of the holes has been put forward, based on a fast calculation of loopholes, probes into the number of holes algorithm with Self set number and the relationship between the number and the matching relation and threshold.Finally, test the improved algorithm in simulation experiment to shows the effectiveness of the algorithm through theoretical analysis and experimental data.更多还原