dbristol/aisec-training-data
收藏Hugging Face2026-04-22 更新2026-04-26 收录
下载链接：
https://hf-mirror.com/datasets/dbristol/aisec-training-data
下载链接
链接失效反馈官方服务：
资源简介：
一个监督微调数据集，用于训练语言模型执行结构化跨框架AI安全和风险管理分析。涵盖四个框架：NIST AI RMF 1.0（AI风险治理）、MITRE ATLAS（对抗性ML威胁、TTPs和检测）、OWASP AI Exchange（运行时攻击面和技术控制）和Google SAIF（安全AI框架组件责任模型）。数据集采用HuggingFace标准的聊天消息格式，包含训练、验证和测试三个分割，总计8,744条记录。
A supervised fine-tuning dataset for training language models to perform structured cross-framework AI security and risk management analysis. Covers four frameworks: NIST AI RMF 1.0 (AI risk governance), MITRE ATLAS (adversarial ML threats, TTPs, and detection), OWASP AI Exchange (runtime attack surfaces and technical controls), and Google SAIF (Secure AI Framework component responsibility model). The dataset uses the HuggingFace-standard chat messages format and includes train, validation, and test splits, totaling 8,744 records.
提供机构：
dbristol
