Phishing attack is now a big threat to people’s daily life and networking environment. Through disguising illegal URLs as legitimate ones, attackers can induce users to visit the phishing URLs to get private information and other benefits. Effective methods of detecting phishing websites are urgently needed to alleviate the threats posed by phishing attacks. As the active learning capability from massive data sets, the neural network is widely used to detect phishing attacks. However, in the stage of training data sets, many useless and small influence features will trap the neural network model into the problem of over-fitting. This problem usually causes the trained model that cannot effectively detect the phishing websites. In order to alleviate this problem, this paper proposes OFS-NN, an effective phishing websites detection model based on optimal feature selection method and neural network. In the proposed OFS-NN, a new index (FVV, Feature Validity Value) is firstly introduced to evaluate the impact of sensitive features on phishing websites detection. Then, based on the new FVV index, an algorithm is designed to select optimal features from the phishing websites. This algorithm is able to alleviate the over-fitting problem of the underlying neural network to a large extent. The selected optimal features are used to train the underlying neural network and, finally, an optimal classifier is constructed to detect the phishing websites. The experimental results show that the OFS-NN model is accurate and stable in detecting many types of the phishing websites.

In this paper, a parallel genetic algorithm for finding all roots of complex functional equation based on Parallel Virtual Machine (PVM) is present, research are made in some technical problems for realizing. We describe the design and implement of parallel genetic algorithm for finding roots complex functional equation.

The detection of surface defects in urban tunnels is a key focus of safety operations and maintenance. Structural surface defect detection has gone through three key phases: manual visual inspection phase, manual instrumental inspection phase, and image visual perception phase, with most current studies focusing on the third phase. This paper analyses the current situation and problems of existing surface defects detection technologies at two levels: traditional image processing and intelligent machine vision perception. Correspondingly, future trends in surface defect detection techniques for urban tunnels are discussed, which provide solutions for the development of intelligent perception of the structural safety status of urban tunnels.