相关数据集
agent-egress-bench
一个用于评估AI代理出口安全工具的标准测试语料库。包含16个类别的143个案例，涵盖秘密泄露、提示注入、SSRF、MCP工具中毒、链检测、A2A协议扫描、WebSocket DLP、编码逃避、shell混淆以及加密货币/金融数据保护。
github2026-03-31 更新530
innodatalabs/rt2-attaq-instruction-complex
该数据集是用于红队测试的AttaQ-instruction-dataset数据集，生成自https://huggingface.co/datasets/ibm/AttaQ和https://huggingface.co/datasets/HuggingFaceH4/instruction-dataset。数据集的结构包括消息、预期结果和ID，消息部分包含角色和内容。数据集的主要用途是测试和评估模型在
Hugging Face2025-01-22 更新170
Water Modelling-Modelled Data-Long-term average annual extraction limit (LTAAEL)-Peel
Long-term average annual extraction limit (LTAAEL) is a regulatory limit set on annual water extractions from a river system. It ensures that average extractions over the long term are sustainable, an
Research Data Australia80
vfleaking/GSM-Danger
--- dataset_info: features: - name: instruction dtype: string splits: - name: test num_bytes: 35483 num_examples: 100 download_size: 23203 dataset_size: 35483 configs: - config
Hugging Face2024-03-01 更新220
A Curation-Needs Assessment of Historical Collections at Select Facilities for the US Department of Veterans Affairs
At the request of the U.S. Department of Veterans Affairs (VA), the U.S. Army Corps of Engineers, St. Louis District, Mandatory Center of Expertise for the Curation and Management of Archaeological Co
DataONE2017-08-14 更新110
