theResearchNinja/benchmarkResults_violentUTF_cybersecurityBehavior
收藏Hugging Face2025-11-08 更新2025-11-15 收录
下载链接：
https://hf-mirror.com/datasets/theResearchNinja/benchmarkResults_violentUTF_cybersecurityBehavior
下载链接
链接失效反馈官方服务：
资源简介：
该数据集是用于评估大型语言模型在处理以人为中心的复杂相互依赖的网络安全场景中的表现的一个评估框架，名为ViolentUTF-CEM。它旨在通过评估LLM在理解与人类因素相关的网络安全场景方面的能力，来提高这些模型在网络安全威胁建模和风险管理中的可靠性。
This dataset is an evaluation framework named ViolentUTF-CEM, designed to assess the performance of large language models in handling human-centric complex interdependent cybersecurity scenarios. It aims to enhance the reliability of these models in cybersecurity threat modeling and risk management by evaluating their ability to understand cybersecurity scenarios related to human factors.
提供机构：
theResearchNinja
