ABSTRACT
Intrusion detection is one of the core technologies in dynamic
security. As an important branch of artificial intelligence, neural
networks is a high efficient and parallel, non-linear dynamical
system, it possesses characteristics of self-adaptive, self- learning
and well expansibility. Aimed at the traditional IDS defects of
high rate of false alarm and high rate of missing report, we design
the method of IDS based on BP neural networks. For huge data
samples, the training of the value of the weight is improved
compared with the traditional back-propagation (BP) neural
networks and simulation, the results show that the method is
efficient.