CS-Eval 大模型网络安全评测数据集
收藏资源简介:
CS-Eval 是由阿里安全、复旦大学和中国科学院大学联合建立的大模型网络安全能力评测集。数据集覆盖 11 个网络安全大类领域、 42 个子类领域,4,369 多项选择题、判断题、知识抽取题,提供知识型和实战型的综合评估任务,支持用户自主评测,同时为大模型落地网络安全提供参考和启发。
CS-Eval is a cybersecurity capability evaluation dataset for large language models jointly established by Alibaba Security, Fudan University, and the University of Chinese Academy of Sciences. The dataset covers 11 high-level cybersecurity domains and 42 sub-domains, including 4,369 multiple-choice questions, true-false questions, and knowledge extraction questions. It provides comprehensive assessment tasks covering both knowledge-based and practical scenarios, supports users to conduct self-evaluation, and offers references and inspirations for the deployment of large language models in the field of cybersecurity.




