知识库
计算机科学
知识获取
构造(python库)
开放式知识库连接
基于知识的系统
知识管理
桥(图论)
领域知识
答疑
知识抽取
知识工程
个人知识管理
数据科学
计算机安全
万维网
组织学习
人工智能
医学
内科学
程序设计语言
作者
Zhengjie Ji,Edward Choi,Peng Gao
标识
DOI:10.1109/icde53745.2022.00287
摘要
Open-source cyber threat intelligence (OSCTI) provides a form of evidence-based knowledge about cyber threats, enabling businesses to gain visibility into the fast-evolving threat landscape. Despite the pressing need for high-fidelity threat knowledge, existing cyber threat knowledge acquisition systems have primarily focused on providing low-level, isolated indicators. These systems have ignored the rich higher-level threat knowledge entities and their relationships presented in OSCTI reports, and do not provide a flexible and intuitive way for threat analysts to acquire the desired knowledge. To bridge the gap, we propose ThreatQA, a system that facilitates cyber threat knowledge acquisition via knowledge base question answering. Particularly, ThreatQA uses a combination of AI-based techniques to (1) automatically harvest comprehensive knowledge about trending threats from massive OSCTI reports from various sources and construct a large threat knowledge base, and (2) intelligently respond to an input natural language threat knowledge acquisition question by fetching the answer from the threat knowledge base via question answering.
科研通智能强力驱动
Strongly Powered by AbleSci AI