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

Z Shen, Z Xi, Y He, W Tong, J Hua, S Zhong - arXiv preprint arXiv …, 2024 - arxiv.org
The rapid adoption of online chatbots represents a significant advancement in artificial
intelligence. However, this convenience brings considerable privacy concerns, as prompts …

An Inversion Attack Against Obfuscated Embedding Matrix in Language Model Inference

Y Lin, Q Zhang, Q Cai, J Hong, W Ye… - Proceedings of the …, 2024 - aclanthology.org
With the rapidly-growing deployment of large language model (LLM) inference services,
privacy concerns have arisen regarding to the user input data. Recent studies are exploring …

WiP: An On-device LLM-based Approach to Query Privacy Protection

Y Yuan, R Kong, Y Li, Y Liu - Proceedings of the Workshop on Edge and …, 2024 - dl.acm.org
Privacy leakage from user queries is a widely-concerned issue in search engines and
chatbot services. Existing solutions based on privacy information removal, obfuscation, and …