基于IRBF的入侵检测系统的研究．

RESEARCH ON IRBF-BASED INTRUSION DETECTION SYSTEM

入侵检测是一种积极、动态的网络安全防护技术,能够对网络内外攻击进行防御,在保障网络安全方面起着重要的作用。研究一种将基于克隆选择原理的免疫识别算法应用于RBF(Radial Basis Function)神经网络的学习算法。该算法将输入数据作为抗原,抗体作为RBF神经网络的隐层中心,采用最小二乘递推法确定权值,提高了RBF神经网络收敛速度和精度。该算法被成功地运用到入侵检测系统中。理论与实验表明该算法具有较好的检测能力,可以较好地提高入侵检测的效率,降低误报率。

As an active and dynamic networks security-defense technique, intrusion detection can resist the attacks from inside and outside the networks, and plays an important role in assuring the networks security. We study a learning algorithm which applies the clonal selection principle-based immune recognition algorithm to radial basis function （RBF） neural network. This algorithm uses input data as the antigens and antibodies as the hidden layer centres of RBF neural network＇., adopts recursive least square method to determine the weights, improves the convergence speed and precision of RBF neural network. This algorithm has been successfully applied to the intrusion detection systems. Theory and experiment show that this algorithm has better ability in intrusion detection, and can be used to improve the efficiency of intrusion detection, reduce the false alarm rate.