Abstract: An intrusion detection based on BP neural network and Bagging method is proposed.BP neural network is used as the classifier and the link action of network is used as the feature.In order to improve the performance of BP neural network classifier，Bagging method is used to integrate BP neural network.Then the evaluation method and results are given.The evaluation results show that the performance of the proposed method is effective.

摘要： 提出基于Bagging算法集成BP神经网络的入侵检测方法。采用BP神经网络为分类器，以用户的网络连接行为为特征进行检测，为进一步提高BP神经网络的分类性能，采用Bagging算法对BP神经网络分类器进行加权投票。实验表明，提出的方法具有良好的检测性能。