Phishing is a kind of online attack that attempts to defraud sensitive information of network users. Current phishing webpage detection methods mainly use manual feature collection, and there are problems that feature extraction is complicated and the possible correlation between features cannot be avoided. To solve the problems, a new phishing webpage detection model is proposed, among which the main components are automatic learning representations from multi-aspects features through representation learning and extracting features by hybrid deep learning network. Firstly, the model treats URL, HTML page content, and DOM (Document Object Model) structure of webpages as character sequences respectively, and uses representation learning technology to automatically learn the representation of the webpages; then, sends multiple representations to a hybrid deep learning network composed of a convolutional neural network and a bidirectional long and short-term memory network through different channels to extract local and global features, and use the attention mechanism to strengthen the influence of important features; finally, the output of multiple channels is fused to realize classification prediction. Through four sets of experiments to verify the detection effect of the model, the results show that the overall classification effect of the model is better than the existing classic phishing webpage detection methods, the accuracy reaches 99.05%, and the false positive rate is only 0.25%. It is proved that the strategies of extracting webpage features from all aspects through representation learning and hybrid deep learning network can effectively improve the detection effect of phishing webpages.

In response to the insufficient consideration of spatio-temporal dependencies and traffic pattern similarity in traffic flow prediction methods based on federated learning, as well as the neglect of model heterogeneity and objective heterogeneity, a traffic flow prediction model based on federated learning and spatio-temporal graph neural networks is proposed. The model is divided into two stages. In the road network division stage, the traffic road network is divided into subnetworks by the dynamic time warping algorithm and the K-means algorithm, to ensure the same subnetwork has the similar traffic flow pattern. The federated learning stage is divided into two sub-stages. In the local training phase, the spatio-temporal graph neural network with an attention mechanism is utilized to create personalized models and meme models to capture the spatio-temporal dependencies of each subnetwork. At the same time, deep mutual learning is utilized to address model heterogeneity and objective heterogeneity through knowledge distillation. In the global aggregation phase, a multi-factor weighted aggregation strategy is designed to measure the contribution of each local model to the global model, to enhance the fairness of aggregation. Three sets of experiments were conducted on two real datasets, and the experimental results demonstrate that the proposed model outperforms the baseline models in three common evaluation metrics.

Phishing is a kind of cyber-attack that targets naive online users by tricking them into revealing sensitive information. There are many anti-phishing solutions proposed to date, such as blacklist or whitelist, heuristic-based and machine learning-based methods. However, online users are still being trapped into revealing sensitive information in phishing websites. In this paper, we propose a novel phishing webpage detection model, based on features that are extracted from URL, source codes of HTML, and the third-party services to represent the basic characters of phishing webpages, which uses a deep learning method – Stacked Autoencoder (SAE) to detect phishing webpages. To make features in the same order of magnitude, three kinds of normalization methods are adopted. In particular, a method to calculate correlation coefficients between weight matrixes of SAE is proposed to determine optimal width of hidden layers, which shows high computational efficiency and feasibility. Based on the testing of a set of phishing and benign webpages, the model using SAE achieves the best performance when compared to other algorithms such as Naive Bayes (NB), Support Vector Machine (SVM), Convolutional Neural Networks (CNN), and Recurrent Neural Networks (RNN). It indicates that the proposed detection model is promising and can be applied effectively to phishing detection.

Research on topic evolution of Microblog is an effective way to analyze network public opinions. This paper proposes a method for mining changing of Microblog topics with time, and realizes topic evolution through topic extraction and topic relevance calculation. Firstly, latent Dirichlet allocation (LDA) model is used to automatically extract topics from different time slices; secondly, a similarity calculation algorithm is designed to calculate relevance of topic content through normalization of similarities among characteristic words and co-occurrence relations, to get evolutionary relationship among sub-topics of different time slices; thirdly, using probability distribution of blog article-topic to calculate topic intensity in each time slice, and then gets evolutionary relationship of topic intensity over time. Experiments show that the proposed topic evolution analysis model can effectively detect the evolution of topic content and intensity of real blogs.

Link prediction aims to predict the missing edge or the edge that may be generated in the future. The key to link prediction is to obtain the characteristic information with strong representation for nodes. In this work, aiming at the problem that the existing link prediction methods fail to take full account of the high-order connection mode of nodes, we present a new representation learning-based approach called OC-GAE (Orbit Counting and Graph Auto-Encoder) that considers rich subgraph structure around nodes. Firstly, the number of orbits on subgraphs is calculated as the high-order structural features of the nodes; then, the number of orbits is used as the input of Graph Auto-Encoder to learn the efficient representation of the nodes; finally, the network adjacency matrix is reconstructed by the learned representation to realize the link prediction. By comparing with five classical link prediction methods and two mainstream network representation learning methods on four real network datasets, the effectiveness of the proposed method and the prediction accuracy are proved to be optimal in general.

Traffic prediction is the key for Intelligent Transport Systems (ITS) to achieve traffic control and traffic guidance, and the key challenge is that traffic flow has complex spatial-temporal dependence and nonlinear dynamics. Aiming at the lack of the ability to model complex and dynamic spatial-temporal dependencies in current research, this paper proposes a traffic flow prediction model Attention based Graph Convolution Network (GCN) and Transformer (AGCN-T) to model spatial-temporal network dynamics of traffic flow, which can extract dynamic spatial dependence and long-distance temporal dependence to improve the accuracy of multistep traffic prediction. AGCN-T consists of three modules. In the spatial dependency extraction module, according to the similarity of historical traffic flow sequences of different loop detectors, an adjacency matrix for the road network is constructed based on a sequence similarity calculation method, Predictive Power Score (PPS), to express latent spatial dependency; and then GCN is used on the adjacency matrix to capture the global spatial correlation and Transformer is used to capture dynamic spatial dependency from the most recently flow sequences. And then, the dynamic spatial dependency is merged with the global spatial correlation to obtain the overall spatial dependency pattern. In the temporal dependency extraction module, the temporal dependency pattern of each traffic flow sequence is learned by the temporal Transformer. The prediction module integrates both patterns to form spatial-temporal dependency patterns and performs multistep traffic flow prediction. Four sets of experiments are performed on three actual traffic datasets to show that AGCN-T can effectively capture the dynamic spatial-temporal dependency of the traffic network, and its prediction performance and efficiency are better than existing baselines. AGCN-T can effectively capture the dynamics in traffic flow. In addition to traffic flow prediction, it can also be applied to other spatial-temporal prediction tasks, such as passenger demand prediction and crowd flow prediction.