【摘 要】
:
With the rapid development of Internet technology and the advent of the era of big data, more and more cyber security texts are provided on the Internet. These
【机 构】
:
School of Software,Yunnan University,Kunming 650091,China;School of Software,Yunnan University,Kunmi
论文部分内容阅读
With the rapid development of Internet technology and the advent of the era of big data, more and more cyber security texts are provided on the Internet. These texts include not only security concepts, incidents, tools, guidelines, and policies, but also risk management approaches, best practices, assurances, technologies, and more. Through the integration of large-scale, hetero-geneous, unstructured cyber security information, the identification and classification of cyber security entities can help handle cyber security issues. Due to the complexity and diversity of texts in the cyber security domain, it is difficult to identify security entities in the cyber security domain using the traditional named entity recognition (NER) methods. This paper describes various approaches and techniques for NER in this domain, including the rule-based approach, dictionary-based approach, and machine learning based approach, and discusses the problems faced by NER research in this domain, such as conjunction and disjunction, non-standardized naming convention, abbreviation, and massive nesting. Three future directions of NER in cyber security are proposed: (1) application of unsupervised or semi-supervised technology; (2) development of a more comprehensive cyber secu-rity ontology; (3) development of a more comprehensive deep learning model.
其他文献
The prediction of regional traffic flows is important for traffic control and management in an intelligent traffic system. With the help of deep neural networks
Since Israelachvili and co-workers in 1970s first developed apparatuses to detect van der Waals forces of molecularly smooth mica surfaces confined down to 1.5 nm, these advanced surface techniques have been vastly explored and extended to detect a variet
The microbubble and microinterface play key roles in the development and progress of the technology in the field of chemical engineering,which has attracted bro
In recent years,transition-metal oxides (TMOs) have been long employed for aerobic oxidative desulfurization.However,the inherent bottlenecks,such as the low ex
某污水厂近期设计用地规模为10000 m3/d,远期处理用地规模为30000 m3/d,用地紧张。通过采用反应沉淀一体式矩形环流生物反应器(RPIR)和磁混凝澄清池的工艺设计,有效解决了污水厂用地紧张的问题,出水稳定达标,可为其他类似污水厂设计提供新思路。
We like to highlight the extension of COSMO-based models (COSMO RS-FV and COSMO SAC-FV) to the prediction of gas solubility in polymers,including polymerized io
Hydrogen production by water electrolysis is a compelling technology to produce fuels and chemicals powered by renewable energy.It is highly desirable to develo
Nitrogen-doped lignin-based carbon microspheres are synthesized using 3-aminophenol as a nitrogen source by the hydrothermal method.The structural change and the effect on the electrochemical properties are systematically investigated. Nitrogen-doped lign
In this study,cellulose nanofibrils (CNF) of high charge (H-P-CNF) and screened size (H-P-CNF-S) were fabricated by increasing the charge of phosphorylated cell