改进BP算法在入侵检测技术中的应用

Application of improved BP algorithm in intrusion detection technology

针对传统BP算法收敛速度慢且容易陷入局部极小的缺点,提出了一种基于Cauchy鲁棒误差估计标准方法的改进BP算法。传统BP算法之所以收敛速度慢及容易陷入局部极小,主要原因在于采用的误差估计标准过度重视了样本的异常值,而Cauchy鲁棒统计误差估计能够减少样本异常值的影响,在一定程度上摆脱对初始权值和阈值的依赖性,进而提高算法训练样本的速度和入侵检测的精度。将改进后的BP算法用于入侵检测中以解决入侵检测系统要求较高的实时性难题。仿真实验取得了较好的效果。

Intrusion detection plays an important part in network security today. BP algorithm, which is an algorithm in artificial intelligences, can also be used in IDS. This paper makes use of improved BP algorithm compared to the traditional one and the new algorithm brings us higher speed in constringency and more preciseion in detection .The new algorithm solves the difficulties of real-time system. The simulation result verities its validation.