Generating Privacy-Preserving Personalized Advice with Zero-Knowledge Proofs and LLMs

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Watanabe, Hiroki, Uchikoshi, Motonobu
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910917666537472
author Watanabe, Hiroki
Uchikoshi, Motonobu
author_facet Watanabe, Hiroki
Uchikoshi, Motonobu
contents Large language models (LLMs) are increasingly utilized in domains such as finance, healthcare, and interpersonal relationships to provide advice tailored to user traits and contexts. However, this personalization often relies on sensitive data, raising critical privacy concerns and necessitating data minimization. To address these challenges, we propose a framework that integrates zero-knowledge proof (ZKP) technology, specifically zkVM, with LLM-based chatbots. This integration enables privacy-preserving data sharing by verifying user traits without disclosing sensitive information. Our research introduces both an architecture and a prompting strategy for this approach. Through empirical evaluation, we clarify the current constraints and performance limitations of both zkVM and the proposed prompting strategy, thereby demonstrating their practical feasibility in real-world scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2502_06425
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generating Privacy-Preserving Personalized Advice with Zero-Knowledge Proofs and LLMs
Watanabe, Hiroki
Uchikoshi, Motonobu
Cryptography and Security
Artificial Intelligence
Large language models (LLMs) are increasingly utilized in domains such as finance, healthcare, and interpersonal relationships to provide advice tailored to user traits and contexts. However, this personalization often relies on sensitive data, raising critical privacy concerns and necessitating data minimization. To address these challenges, we propose a framework that integrates zero-knowledge proof (ZKP) technology, specifically zkVM, with LLM-based chatbots. This integration enables privacy-preserving data sharing by verifying user traits without disclosing sensitive information. Our research introduces both an architecture and a prompting strategy for this approach. Through empirical evaluation, we clarify the current constraints and performance limitations of both zkVM and the proposed prompting strategy, thereby demonstrating their practical feasibility in real-world scenarios.
title Generating Privacy-Preserving Personalized Advice with Zero-Knowledge Proofs and LLMs
topic Cryptography and Security
Artificial Intelligence
url https://arxiv.org/abs/2502.06425