Benchmarking and defending against indirect prompt injection attacks on large language models

J Yi, Y Xie, B Zhu, K Hines, E Kiciman, G Sun… - arXiv preprint arXiv …, 2023 - arxiv.org
Recent remarkable advancements in large language models (LLMs) have led to their
widespread adoption in various applications. A key feature of these applications is the …
被引用次数：29 相关文章 HTML 版

Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models

J Yi, Y Xie, B Zhu, K Hines, E Kiciman, G Sun… - arXiv e …, 2023 - ui.adsabs.harvard.edu
Recent remarkable advancements in large language models (LLMs) have led to their
widespread adoption in various applications. A key feature of these applications is the …
[PDF] github.io

[PDF][PDF] Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models

J Yi, Y Xie, B Zhu, K Hines, E Kiciman, G Sun, X Xie… - xyq7.github.io
Recent remarkable advancements in large language models (LLMs) have led to their
widespread adoption in various applications. A key feature of these applications is the …