Website fingerprint identification defense system and method based on data poisoning

The invention discloses a website fingerprint identification defense system and method based on data poisoning, the system comprises a data poisoning model training module and a defense deployment module, firstly, data poisoning model training is carried out, and a local target WF classifier DF and a data poisoning model are used for training together; storing the trained data poisoning model; and then, performing defense deployment. Compared with the prior art, the method has the advantages that the effect of high protection success rate is achieved by using lower bandwidth overhead under low data collection overhead, on the other hand, the method is a defense method irrelevant to website data, defense scheduling does not need to be updated regularly, and the data collection overhead is low. 本发明公开了一种基于数据投毒的网站指纹识别防御系统及方法，该系统包括数据投毒模型训练模块和防御部署模块，首先，进行所述数据投毒模型训练，分别使用本地目标WF分类器DF与数据投毒模型一起进行训练，保存训练好的数据投毒模型；然后，进行防御部署。与现有技术相比，本发明在低数据收集开销下使用较低的带宽开销达到高保护成功率的效果，另一方面是网站数据无关的防御方法，不需要定期更新防御调度，数据收集开销低。