CTIBench
收藏资源简介:
CTIBench是由罗切斯特理工学院创建的一个专门用于评估大型语言模型(LLMs)在网络威胁情报(CTI)应用中性能的数据集。该数据集包含2500条记录,涵盖了多个子任务,如知识评估、威胁报告分析和漏洞严重性预测等。数据集内容丰富,来源于权威的CTI框架和标准,如NIST、MITRE和GDPR等。创建过程中,研究者利用了GPT-4等先进技术来生成和验证数据集中的问题。CTIBench的应用领域广泛,旨在通过自动化分析提高安全事件响应的效率,帮助组织快速识别和应对网络威胁。
CTIBench is a dataset developed by Rochester Institute of Technology, specifically designed to evaluate the performance of Large Language Models (LLMs) in cyber threat intelligence (CTI) applications. It contains 2500 records covering multiple subtasks including knowledge evaluation, threat report analysis, vulnerability severity prediction and more. The dataset features comprehensive content sourced from authoritative CTI frameworks and standards such as NIST, MITRE and GDPR. During its creation, researchers utilized advanced technologies including GPT-4 to generate and validate the questions within the dataset. CTIBench has a wide range of application scenarios, aiming to improve the efficiency of security incident response through automated analysis and help organizations rapidly identify and address cyber threats.




