Research on Threat Information Network Based on Link Prediction

Research on Threat Information Network Based on Link Prediction

Jin Du (Institute of Software, Chinese Academy of Science, Beijing, China & Yunnan Police College, Kunming, China), Feng Yuan (Institute of Software Application Technology, Guangzhou, China & Chinese Academy of Sciences, Guangzhou, China), Liping Ding (Institute of Software Application Technology, Guangzhou, China & Chinese Academy of Sciences, Guangzhou, China), Guangxuan Chen (Institute of Software, Chinese Academy of Science, Beijing, China & Zhejiang Police College, Hangzhou, China) and Xuehua Liu (Institute of Software, Chinese Academy of Sciences, Beijing, China & University of Chinese Academy of Sciences, China)
Copyright: © 2021 |Pages: 9
DOI: 10.4018/IJDCF.2021030106
Article PDF Download
Open access articles are freely available for download

Abstract

The study of complex networks is to discover the characteristics of these connections and to discover the nature of the system between them. Link prediction method is a classic in the study of complex networks. It ca not only reflect the relationship between the node similarity. More can be estimated through the edge, which reveals the intrinsic factors of network evolution, namely the network evolution mechanism. Threat information network is the evolution and development of the network. The introduction of such a complex network of interdisciplinary approach is an innovative research perspective to observe that the threat intelligence occurs. The characteristics of the network show, at the same time, also can predict what will happen. The evolution of the network for network security situational awareness of the research provides a new approach.
Article Preview
Top

With the Internet as the representative of the rapid development of network information technology, human society has entered a complex network era. Human life and production activities are increasingly dependent on complex systems. As an interdisciplinary emerging field, network science and engineering have been gradually formed and developed rapidly.

The network topology has expanded people's understanding of complex systems, and complex networks are more in-depth to describe the essence of complex systems. Network science is not only an extension of classical graph theory and stochastic graph theory in mathematics, but also an innovative development of system science and complexity science. Scholars through the complex network involved in the economics, biology, physics and other disciplines of observation and research, the use of network nodes between the topology to find unknown or future will be generated links, the problem becomes more important research points, this is the link prediction problem. The link prediction problem of complex networks refers not only to the prediction of future links, but also to the predictions of links that already exist but not yet found.

In nature, there are numerous complex systems that cover ecosystems, social networks, economic networks, and so on. Many complex shapes, such as social networks, political networks, and so on, are closely related to our lives. Complex networks are abstractly described by these methods in a scientific way, and the nature of these systems is discovered. And with the complex network of in-depth study, scholars have found that many do not look the same network, but surprisingly has a lot of similar characteristics. The foundation of complex network construction is the connection between individual and individual. However, when the network is built, the incompleteness and uncertainty of the collected information will cause many of the edges that should have existed to disappear, and many errors occur. To a large extent affected the network attributes and the integrity of the network, the study of complex network interference.

In order to solve this problem, scholars in various fields began to study the network link prediction. There are two reasons for the network link prediction to be concerned in each field. First, from the theoretical point of view, the link prediction algorithm can not only accurately describe the “node similarity”, but also in the complex network Prediction, at the same time will reveal the inherent factors of network evolution, that is, the evolution of the network mechanism. In the near future, link prediction is likely to provide a fair and unified platform for the evolution mechanism of the network, and in essence, to promote the study of network evolution mechanism. Second, it is reflected in its practical application value. Network link prediction can not only be used to predict some of the interaction in the biological field, thus saving research time and money, but also applied to the economic network, traffic network research, can bring more intuitive economic benefits and national resources savings. In an evolving online social network, link predictions can be used to determine similarity through the user's historical behavioral attributes, thus determining the likelihood that two users who have never had a relationship become friends (Signoretto et al., 2011; Leskovec et al., 2009; Viswanath et al., 2009; Bader & Kolda, 2007; Chatfleld, 2013; Sharan & Neville, 2008; Bringmann et al., 2010; Juszczyszyn et al., 2011; R˜ummele et al., 2015; Davis et al., 2013).

Complete Article List

Search this Journal:
Reset
Volume 14: 1 Issue (2022)
Volume 13: 6 Issues (2021)
Volume 12: 4 Issues (2020)
Volume 11: 4 Issues (2019)
Volume 10: 4 Issues (2018)
Volume 9: 4 Issues (2017)
Volume 8: 4 Issues (2016)
Volume 7: 4 Issues (2015)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing