A network fishing detection method based on a Schizothorax group algorithm support vector machine

Abstract

The invention discloses a network fishing detection method based on a douche group algorithm support vector machine. The method comprises the following steps of firstly, initializing basic parametersof the douche group algorithm, including population number, iteration times, individual dimension and search space; randomly initializing the position and range of the individual; and then dividing into leader vessel sea sheaths and follower vessel sea sheaths according to the magnitude of the fitness value, and excavating the optimal parameters of the support vector machine by using the coordination and cooperation of the two vessel sea sheaths. In each iteration, the function for evaluating the fitness value of the individual is the detection accuracy of the parameter carried by the individual on the phishing website data set by the support vector machine. Compared with the common optimization algorithms such as a genetic algorithm, a gravitation search algorithm, a bat algorithm and a particle swarm algorithm, the optimal parameter parameters of the support vector machine can be mined as much as possible on the optimized support vector machine, and the fishing detection accuracy ofthe support vector machine is improved.

Description

technical field [0001] The invention belongs to the technical fields of intelligent optimization, machine learning and information security, and relates to a phishing detection method, in particular to a phishing detection method based on a salp swarm algorithm support vector machine. Background technique [0002] A phishing website is a malicious website that defrauds users of their personal information by imitating a real webpage. With the development of the Internet, more and more people conduct transactions or register online, and at the same time store their account passwords or enter their personal information online. Then criminals create malicious web pages that are very similar to real web pages to defraud users of information. According to statistics, as of 2015, the number of phishing websites has reached more than 260,000, and the number is still increasing significantly, which has caused great hidden dangers to users' information security. [0003] With the ri...

AI Technical Summary

Problems solved by technology

Traditional grid search, particle swarm algorithm, genetic algorithm, etc. all try to optimize the parameters of the support vector machine, but it is easy to fall into a local optimum, and it is difficult to make the support vector machine take full advantage

Images