Xiaoyuan Wu
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper proposes Information Sufficiency (IS) as a comprehensive framework for privacy-preserving LLM communication, demonstrating that free-text pseudonymization outperforms existing suppression and generalization methods, especially in multi-turn conversations.
This paper identifies and categorizes digital security and privacy questions asked to large language models using a dataset of user-LLM conversations, and evaluates the response quality and consistency of commercial and open-source models.
Papers
Security and Privacy Prompts in the Wild: What Users Ask LLMs and How LLMs Respond
Hobin Kim, Xiaoyuan Wu, Omer Akgul, Lujo Bauer +1 more
This paper identifies and categorizes digital security and privacy questions asked to large language models using a dataset of user-LLM conversations, and evaluates the response quality and consistenc…