Abstract: In order to improve the detection performance of intrusion prevention systems,an intrusion prevention model which combines immune danger theory and negative selection mechanism was proposed.It uses the danger theory for anomaly detection and negative selection mechanism for misuse detection,which improves the detection performance.The implementation and key technologies of the model are given,and the simulation experiments are done.The experimental data included the data collected from the actual network and KDDCup intrusion detection evaluation data sets.The results show that the model has a good detection performance.