Abstract: It is always to generate detectors using random strings in intrusion detection system based on artificial immune system.It is slow to generate detectors by this method，and the detection rate of the detector set is poor.There is information about non-self space in non-self samples，so use gene library which is initialized by non-self samples to generate detectors.And use those detectors to detect intrusions.It is proved by experiences with KDD Cup 1999 intrusion detection data set that this method can generate detectors more quickly and effectively and the generated detector set is with higher positive detection rate.

Key words: intrusion detection, artificial immune, generate detector, gene library, KDD Cup 1999

摘要： 在基于人工免疫的入侵检测研究领域，一般都是应用随机产生字符串的方法来生成检测器。这种方法生成检测器的速度较慢，而且生成的检测器集的检测率低。由于非我样本中存在着关于非我空间的信息，提出通过应用非我样本来初始化基因库并应用基因库来生成检测器的方法来检测入侵。应用KDD Cup 1999入侵检测数据集，通过实验证明该方法是有效的，能更快地生成检测率更高的检测器集。

关键词: 入侵检测, 人工免疫, 检测器生成, 基因库, KDD Cup 1999