遇见数据集

Zen0/AusCyberBench

收藏
Hugging Face2025-10-24 更新2025-10-25 收录
官方服务:

资源简介:

AusCyberBench是一个针对大型语言模型(LLM)在澳大利亚网络安全环境中表现的评估基准,包含13,449个经过专家精选的任务,涵盖合规性、技术安全、CTF挑战和知识评估等多个方面。同时,它还包含一个专注于澳大利亚的子集,有4,899个任务,专门用于测试对澳大利亚法规框架、合规要求和威胁情报的知识。

AusCyberBench is a comprehensive benchmark designed for evaluating the performance of Large Language Models (LLMs) in Australian cybersecurity contexts, containing 13,449 expert-curated tasks across regulatory compliance, technical security, CTF challenges, and knowledge assessment. It also includes an Australian-focused subset with 4,899 tasks, specifically for testing knowledge of Australian regulatory frameworks, compliance requirements, and threat intelligence.

提供机构:
Zen0
二维码
社区交流群
二维码
科研交流群
商业服务