Research On Phishing Website Identification Based On Intelligent Algorithm

With the rapid development of the Internet,online transactions have become a common transaction method in people's lives,but at the same time it has brought many security problems.Phishing websites are one of the most serious problems.Phishing websites are one of the most serious problems.The criminals use the network address or page content similar to the regular website to create a phishing website,so that people can fall into the trap of criminal design without any precautions.Implementing information theft on users threatens the security of users' property,and phishing websites also threaten the development of industries related to online transactions.In order to protect the network trading environment,high-performance phishing website detection model is very necessary.This paper introduces intelligent algorithms to study the problem of phishing websites.Intelligent algorithms are algorithms generated by people to recognize and summarize the laws of nature.Because of its intelligence,high adaptability and versatility,intelligent algorithms have been widely used in finance,internet and industry.Based on the BP neural network model,this paper introduces genetic algorithm and particle swarm optimization algorithm to optimize the network parameters of BP neural network from the perspective of optimizing network parameters,and constructs GA-BP model and PSO-BP model.From the perspective of neural network structure,the SVM-RFE algorithm is introduced to reduce the dimension of the sample features,and the SVM-RFE-BP model is constructed by combining with BP neural network.BP neural network and SVM model were selected as control models.The accuracy,accuracy,recall rate and false positive rate are selected as performance evaluation indicators to analyze the SVM-RFE-BP model,and the optimal SVM-RFE-BP model is obtained.The accuracy,model training time and AUC are selected as evaluation indicators to evaluate the performance of BP model,SVM model,GA-BP model,PSO-BP model and SVM-RFE-BP model.The experimental results are analyzed and discussed.It is concluded that the SVM-RFE-BP model has a good effect on the detection of phishing websites.