The Fire Thief Is Also the Keeper: Balancing Usability and Privacy in Prompts

arXiv:2406.14318v1 Announce Type: new
Abstract: The rapid adoption of online chatbots represents a significant advancement in artificial intelligence. However, this convenience brings considerable privacy concerns, as prompts can inadvertently contain sensitive information exposed to large language models (LLMs). Limited by high computational costs, reduced task usability, and excessive system modifications, previous works based on local deployment, embedding perturbation, and homomorphic encryption are inapplicable to online prompt-based LLM applications.
To address these issues, this paper introduces Prompt Privacy Sanitizer (i.e., ProSan), …

adoption advancement artificial artificial intelligence arxiv can chatbots computational computational costs convenience cs.ai cs.cl cs.cr exposed fire high information intelligence keeper language language models large llms privacy privacy concerns prompts rapid sensitive sensitive information task thief usability