构建了基于免疫算法和神经网络的新型抗体网络入侵检测系统，系统与网络入侵检测功能相结合，应用于大型网络的入侵检测任务，具有良好的可扩充性；重点讨论了新型抗体网络原理，引进BP神经网络自学习能力，对已有的抗体网络模型进行改进；通过对网络数据集的测试表明，该算法相对于传统抗体网络，其检测效率得到了明显的改善。This paper designs an antibody network base on immune algorithm and neural network used for Intrusion Detection System. The Abnet network system combines network-based intrusion detection functions. It can be used to protect large area network and has relatively good expansibility. This paper also discusses the theory of the Abnet. How to implement of the Abnet with BP neural network in intrusion detection. Because of the traditional Abnet weakness in learning time and performance, This network is designed. The algorithm has been tested on a network data set. The result showed that it had much better performance than traditional Abnet.