基于遗传神经网络的入侵检测研究

入侵检测技术是计算机网络信息安全检测的重要手段之一,入侵检测作为一种动态的安全防护技术,提供了对内部攻击、外部攻击和误操作的实时保护,在网络系统受到危害之前拦截和响应入侵。对计算机网络数据进行特征提取,提出了采用遗传算法和神经网络相结合入侵检测技术。遗传算法具有计算简单、优化效果好的特点。利用遗传算法来避免BP算法的局部极小点,从而达到均方根误差全局最小点,也解决了BP算法的收敛慢的问题;同时也解决了单独利用GA往往不能在短时间内寻找到接近最优解的这一问题。通过计算机实验验证了入侵检测的效果,提高了识别率,使得误报率和漏报率降低。

Intrusive Detection Based on Genetic Neural Networks

The intrusive detection technology , as an important security measure for computer network information , and a dynamic safety protection technololgy, provides real-time protection to interior and exterior attacks and maloperation, and could intercept and respond the intrusion befere the network system is endangered. By extracting the characteristic of the computer network data the intrusive detection technololgy is formed using the genetic algorithms combined with neural network. The genetic algorithm is easy-to-compute and good in optimization. This algorithm could avoid the local minimum point, and achieve the minimum point of RMS error so as to solve the problem of slow restraint. Moreover, it could solve incapability of seeking nearly optimal solution in short time by GA alone. Through the computer experiment, the effect of intrusive detection is verified, the rate of reccgnition increased, and the rate of misreporting and failed reporting reduced.