While Large Language Models (LLMs) are increasingly being used in real-world
applications, they remain vulnerable to prompt injection attacks: malicious
third party prompts that subvert the intent of the system designer. To help
researchers study this problem, we present a dataset of over 126,000 prompt
injection attacks and 46,000 prompt-based "defenses" against prompt injection,
all created by players of an online game called Tensor Trust. To the best of
our knowledge, this is currently the largest dataset of human-generated
adversarial examples for instruction-following LLMs. The attacks in our dataset
have a lot of easily interpretable stucture, and shed light on the weaknesses
of LLMs. We also use the dataset to create a benchmark for resistance to two
types of prompt injection, which we refer to as prompt extraction and prompt
hijacking. Our benchmark results show that many models are vulnerable to the
attack strategies in the Tensor Trust dataset. Furthermore, we show that some
attack strategies from the dataset generalize to deployed LLM-based
applications, even though they have a very different set of constraints to the
game. We release all data and source code at this https URL

大型语言模型（ LLMS ） 在现实世界应用中越来越多，但仍然容易受到恶意注入攻击的风险。本研究提出了一个由 Tensor Trust 在线游戏的玩家创造的超过 126,000 个注入攻击和 46,000 个注入攻击的防御的数据集，为研究者研究这个问题提供帮助。这是目前最大的人为生成的用于指令跟随 LLMs 的对抗示例数据集。我们利用数据集创建了抵抗两种类型注入攻击的基准测试，并展示了很多模型对于 Tensor Trust 数据集中的攻击策略是脆弱的。此外，我们还展示了数据集中一些攻击策略在不同约束条件的部署 LLMs 应用中也具有普适性。我们在此 https URL 公布了所有的数据和源代码。