基于免疫的入侵检测系统可信问题研究

为了降低入侵检测系统的误报率和漏报率，提出了一种基于人工免疫的新型入侵检测系统模型。借鉴生物免疫系统抗体的演化机制，该模型改进了目前基于免疫的入侵检测系统中抗原、抗体的静态描述方式，给出了抗原、抗体的动态描述方式和变化机制，并针对传统固定r连续位匹配方法的不足，提出了一种r可变匹配机制，最后进行了相关仿真实验。理论分析和实验结果表明,该系统具有较低的误报率和漏报率,提高了入侵检测系统的可信性。

Study of creditability for intrusion detection system based on immunity

To reduce the high false positive rate and false negative rate of intrusion detection systems,this paper proposed an novel intrusion detection system(IDS) based on immunity.Presented the methods to reduce the false positive rate after analyzing creditability of IDS and false positive rate of anomaly IDS.The emphasis on constructing normal profile dynamically based on artificial immunity to restrain false positive rate, then did simulation experiment.The results show that the method can improve the detection efficiency and reduce the false positive rate and false negative rate, so it improves the creditability of IDS.