本文将演化规划应用于入侵检测规则自动提取,利用演化规划灵活的个体表示得到自然描述的规则,使规则易于理解,利用演化规划全局寻优的能力得到较好的入侵检测规则,从而降低误报率和漏报率.文中改进了适应度函数。最后给出了实验结果,并与其它文献的同类实验结果进行了比较,证明了改进演化规划的有效性和先进性.
In this paper, we apply Genetic Programming to distill intrusion detection rules. We make use of flexible encoding of Genetic Programming to gain rules depicted naturally, so that the rules are easy to be understood. And we make use of Genetic Programming's powerful search performance to gain better intrusion detection rules, in order to reduce the false alarm rate(FA) and the detected attacks rate(DR). Our method has the following characteristic: improving fitness function. At last we show experimental results and compare them with other papers. In this way, we prove validity and advantage of our method.