Safeguarding System Prompts for LLMs
Keywords: large language models, system prompts, privacy
TL;DR: PromptKeeper is a novel, effective, and capability-preserving defense mechanism for system prompt privacy.
Abstract: Large language models (LLMs) are increasingly utilized in applications where system prompts, which guide model outputs, play a crucial role. These prompts often contain business logic and sensitive information, making their protection essential. However, adversarial and even regular user queries can exploit LLM vulnerabilities to expose these hidden prompts. To address this issue, we present PromptKeeper, a novel defense mechanism for system prompt privacy. By reliably detecting worst-case leakage and regenerating outputs without the system prompt when necessary, PromptKeeper ensures robust protection against prompt extraction attacks via either adversarial or regular queries, while preserving conversational capability and runtime efficiency during benign user interactions.
Primary Area: alignment, fairness, safety, privacy, and societal considerations
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 72
Loading