five

sureheremarv/ipi_arena_attacks

收藏
Hugging Face2026-03-18 更新2026-04-05 收录
下载链接:
https://hf-mirror.com/datasets/sureheremarv/ipi_arena_attacks
下载链接
链接失效反馈
官方服务:
资源简介:
--- license: mit language: - en tags: - agent - security - prompt-injection size_categories: - n<1K --- # IPI Arena Attacks Attack strings from the [IPI Arena](https://github.com/GraySwanAI/ipi_arena_os) benchmark for evaluating model robustness to indirect prompt injection (IPI), from [How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition](https://arxiv.org/abs/2603.15714). ## Dataset 95 attack strings across 28 behaviors, sourced from Qwen (`qwen/qwen3-vl-235b-a22b-instruct`). These attacks succeeded on open-source models but did **not** transfer to any closed-source model in the arena. Each row contains: - `behavior_id`: the benchmark behavior the attack targets - `attack`: the injection string ## Usage ```python from datasets import load_dataset ds = load_dataset("sureheremarv/ipi_arena_attacks") ``` Or with [ipi-arena-bench](https://github.com/GraySwanAI/ipi_arena_os): ```yaml behaviors: hf_dataset: sureheremarv/ipi_arena_attacks behavior_ids: - garage-door-email - book-hotel ``` ## Citation ```bibtex @misc{dziemian2026vulnerableaiagentsindirect, title={How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition}, author={Mateusz Dziemian and Maxwell Lin and Xiaohan Fu and Micha Nowak and Nick Winter and Eliot Jones and Andy Zou and Lama Ahmad and Kamalika Chaudhuri and Sahana Chennabasappa and Xander Davies and Lauren Deason and Benjamin L. Edelman and Tanner Emek and Ivan Evtimov and Jim Gust and Maia Hamin and Kat He and Klaudia Krawiecka and Riccardo Patana and Neil Perry and Troy Peterson and Xiangyu Qi and Javier Rando and Zifan Wang and Zihan Wang and Spencer Whitman and Eric Winsor and Arman Zharmagambetov and Matt Fredrikson and Zico Kolter}, year={2026}, eprint={2603.15714}, archivePrefix={arXiv}, primaryClass={cs.CR}, url={https://arxiv.org/abs/2603.15714}, } ``` ## Links - Benchmark code: [GraySwanAI/ipi_arena_os](https://github.com/GraySwanAI/ipi_arena_os)
提供机构:
sureheremarv
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作