The invention discloses a phishing detection method based on a salps swarm algorithm support vector machine. First, the basic parameters of the salps swarm algorithm are initialized: the population number, the number of iterations, the individual dimension, and the search space; the position and range of the individual are randomly initialized; Then it is divided into leader salps and follower salps according to the size of the fitness value, and the optimal parameters of the support vector machine are excavated by the coordination and cooperation of these two salps. In each iteration, the function used to evaluate the fitness value of the individual is the detection accuracy of the parameters carried by the individual on the phishing website dataset. The present invention and general optimization algorithms such as genetic algorithm, gravitational search algorithm, bat algorithm, particle swarm algorithm, etc., can dig out the optimal parameter parameters of the support vector machine as much as possible on the optimization support vector machine, and improve the performance of the support vector machine in fishing. detection accuracy.