No abstract

In order to protect computing systems from malicious attacks, network intrusion detection systems have become an important part in the security infrastructure. Recently, hybrid models that integrating several machine learning techniques have captured more attention of researchers. In this paper, a novel hybrid model was proposed with the purpose of detecting network intrusion effectively. In the proposed model, Gini index is used to select the optimal subset of features, the gradient boosted decision tree (GBDT) algorithm is adopted to detect network attacks, and the particle swarm optimization (PSO) algorithm is utilized to optimize the parameters of GBDT. The performance of the proposed model is experimentally evaluated in terms of accuracy, detection rate, precision, F1-score, and false alarm rate using the NSL-KDD dataset. Experimental results show that the proposed model is superior to the compared methods.

No abstract

With the rapid growth of various complex networks, link prediction has become increasingly important because it can discover the missing information and predict future interactions between nodes in a network. Recently, the CAR and CCLP indexes have been presented for link prediction by means of different triangle structure information. However, both indexes may lose the contributions of some shared neighbors. We propose in this work a new index to make up the weakness and then improve the accuracy of link prediction. The proposed index focuses on a new triangle structure, i.e., the triangle formed by one seed node, one common neighbor, and one other node. It emphasizes the importance of these triangles but does not ignore the contribution of any common neighbor. In addition, the proposed index adopts the theory of resource allocation by penalizing large-degree neighbors. The results of comparison with CN, AA, RA, ADP, CAR, CAA, CRA, and CCLP on 12 real-world networks show that the proposed index outperforms the compared methods in terms of AUC and ranking score.

Link prediction is one of the research hotspots in complex network analysis and has a wide range of applications in both theory and reality. To improve the prediction accuracy, this paper proposes a new link prediction framework by considering both node similarity and community information, which overcomes the weaknesses of existing community-based prediction methods. In the proposed framework, a reasonable measure, called community relationship strength (CRS), is defined to estimate the closeness between communities. In this paper, we hold the view that the connection likelihood between two target nodes rests upon not only their similarity but also the closeness of communities that they belong to. Therefore, to measure the connection likelihood, the proposed framework combines CRS with traditional similarity indexes. Three CRS-based methods are derived from the framework. The performance of the CRS-based methods is comprehensively studied on 12 real-world networks compared with several groups of baselines. The experimental results indicate that the CRS-based methods are more effective and robust than others. INDEX TERMS Link prediction, community structure, similarity index, complex networks. I. INTRODUCTION A network is a structure that is composed of nodes and their static or dynamic relations, called edges or links. This simple structure can model a large variety of complex systems such as social, biological and technological systems, in which nodes are entities in these systems and links indicate the relations between entities [1]-[3]. The proliferation of data has inspired the study of network mining and complex network analysis. A wealth of interesting problems related to network mining, such as community detection [4], [5], node rank [6], and network embedding [7], have been studied. Among these interesting network-related problems, link prediction has been receiving increasing interest from disparate disciplines because not only many available real-world networks are incomplete [8], [9], but also its wide range of applications in both theory and reality [10], [11]. For examples, link prediction can be used in exploring network evolution mechanisms [12], [13], finding the cooperation opportunities among scientists [14], [15], recommending friends in social The associate editor coordinating the review of this manuscript and approving it for publication was Lin Wang.