datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
cyberseceval3-visual-prompt-injection
Dataset Card for CyberSecEval 3 - Visual Prompt Injection Benchmark
Dataset Details
Dataset Description
This dataset provides a multimodal benchmark for visual prompt injection, with text/image inputs. It is part of CyberSecEval 3, the third edition of Meta's flagship suite of security benchmarks for LLMs to measure cybersecurity risks and capabilities across multiple domains.
Language(s): English
License: MIT
Dataset Sources
Repository: Link… See the full description on the dataset page: https://huggingface.co/datasets/facebook/cyberseceval3-visual-prompt-injection.MultiPriv
🔐MultiPriv: A Multilingual & Multimodal Dataset of PII Entities and Prompts for LLM Privacy Risk Research
多语言多模态 PII 实体与 Prompt 数据集 —— MultiPriv 数据集（面向大模型的隐私风险研究）
❗Due to the limitations of open-source certificates, attribute-level VLM images cannot be directly published in the repository. We will provide links to each image used in our dataset
由于开源证书限制，属性级 VLM 图像无法直接公布在仓库里，我们会整理我们数据集用到的每一张图片链接
🎉 News
[2026.06] 🎊 Our MultiPriv has been accepted to ICML 2026… See the full description on the dataset page: https://huggingface.co/datasets/CyberChangAn/MultiPriv.