Research On Intrusion Detection Technology Based On Firefly Algorithm And Artificial Immune Algorithm

Nowadays,the continuous development of network technology not only brings convenience,but also brings more security risks.As a kind of defense means,intrusion detection technology is facing a greater test.By studying the new direction and new ideas of intrusion detection technology,it is of great significance to improve the breadth and depth of intrusion detection technology.At present,there are many researches on intrusion detection technology,but there are few researches on Intrusion Detection Based on firefly algorithm and artificial immune algorithm.This paper also studies these two aspects.The main work and innovations of this paper are as follows:(1)Aiming at the problems of easy convergence and high computational cost of the traditional firefly algorithm,the firefly algorithm is improved,and a feature selection scheme based on the firefly algorithm is proposed.The specific improvement methods are as follows:for the initial population,define a vector composed of 0-1 for a single firefly individual,and set a one-to-one correspondence for discrete features;For the step size,the dynamic update step size mechanism is introduced,and the initial step size is set to a higher value,which can better global search in the early stage of the algorithm iteration.After a certain number of iterations,the step size gradually decreases,and then quickly converges to the optimal solution;For the brightness function and selection mode,the distance between classes is introduced as the brightness function to redefine the selection mode.The improved firefly algorithm selects the features of KDDCUP99 data set and obtains 10 optimal features.After training these 10 features,the accuracy is 99.48%.(2)Aiming at the problem of slow convergence of traditional intrusion detection schemes,an intrusion detection technology based on immune algorithm is proposed.Firstly,the clonal selection algorithm is improved.The specific improvement methods are as follows:for the cloning process,the cloning method is changed to non proportional cloning to improve the sub algebra of individual clones with high affinity;For the variation process,we should start with the variation step size and variation frequency to reduce the possibility of unnecessary variation.Then,the classification method is optimized by combining the improved negative selection algorithm with coevolutionary algorithm.A new scheme based on de threat distribution center is proposed.Finally,simulation experiments are carried out to compare the improved clonal selection algorithm with the classical clonal selection algorithm.The improved clonal selection algorithm has fast convergence speed,high detection rate and stability.