针对M IT L inco ln L ab数据集评测方法中背景超文本传输协议(hypertex t transfer protoco l,HTTP)流量在用户建模和流量模拟时会造成偏差,提出了一种基于用户轮廓的W eb流量模拟方法。该方法在应用层进行数据采集并对用户行为特征进行建模生成用户轮廓知识库,模拟时可根据不同网络环境特征扩展生成虚拟用户轮廓。实验分析表明,该方法能同时兼顾流量模拟的扩展性和真实性,生成的数据集流量特征与实际网络相吻合,用于入侵检测系统评测时能有效降低误报率指标。 In the context of the MIT L inco ln L ab dataset evaluation methodology, hypertext transfer protocol (HTTP) traffic may cause biases in user modeling and traffic simulation, and a W eb based on user profile Traffic simulation method. The method collects data in the application layer and models the user behavior features to generate the user profile knowledge base. During the simulation, the virtual user profile can be generated according to the characteristics of different network environments. Experimental results show that the proposed method can take account of the scalability and authenticity of the traffic simulation at the same time. The generated traffic characteristics of the data set are consistent with the actual network, which can effectively reduce the false alarm rate when used in the intrusion detection system evaluation.