SpoofingSpoof websites representsrepresent legitimate web sites which attract users into visiting fake websitessites to steal usersusers' sensitive, personal information or install malwares inmalware to their devices. This paper is concerned onwith presenting an intelligent approach to detect and recognize legitimate and spoofingspoof websites, which try to mimic the trustedtrusted sites because it is very difficult to visually recognize whether they are spoofingspoofs or legitimate. Information gain algorithmgained by algorithms is used for feature selection, which wasis a useful step to remove the unnecessary features. The Information gain seeminformation gained seems to improve the classification accuracy by reducing the number of extracted features and is used as an input for training the neural network using particle swarm optimization. Training neural networknetworks using PSO providesrequires less training time and has good accuracy, which achievedachieves 99% compared to NN trainedtraining with back propagation algorithm which taketakes more time for training and lesshas a lower accuracy which waslevel of 98.1%. The proposed technique is evaluated with a dataset of 2500 spoofingspoof sites and 2500 legitimate sites.