Enhancing Trust in AI Marketplaces: Evaluating On-Chain Verification of Personalized AI models using zk-SNARKs

2025-04-07

AI Summary

Addressing the challenge of simultaneously ensuring integrity and privacy for personalized AI models in decentralized environments, this paper proposes the first on-chain verification framework integrating zk-SNARKs with the Chainlink decentralized oracle network. The framework enables trustworthy, zero-knowledge verification of performance claims about external-data-driven models—without revealing model parameters or relying on trusted third parties. Evaluated on Ethereum’s Sepolia testnet, it achieves end-to-end verification for a linear regression-based Bitcoin price prediction model: average proof generation takes 233.63 seconds, while on-chain verification requires only 61.50 seconds. Throughout, model parameters remain private, and the architecture is designed for scalability to more complex AI models. Our core contribution is the realization of verifiable AI model integrity under strict privacy guarantees, eliminating reliance on plaintext data or centralized trust assumptions prevalent in existing on-chain AI verification approaches.

Technology Category

• Machine Learning: Privacy
• Philosophy and Ethics of AI: Privacy & Security
• Computer Vision: Large Vision Models

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Security and Privacy: Data transparency and provenance

Abstract

The rapid advancement of artificial intelligence (AI) has brought about sophisticated models capable of various tasks ranging from image recognition to natural language processing. As these models continue to grow in complexity, ensuring their trustworthiness and transparency becomes critical, particularly in decentralized environments where traditional trust mechanisms are absent. This paper addresses the challenge of verifying personalized AI models in such environments, focusing on their integrity and privacy. We propose a novel framework that integrates zero-knowledge succinct non-interactive arguments of knowledge (zk-SNARKs) with Chainlink decentralized oracles to verify AI model performance claims on blockchain platforms. Our key contribution lies in integrating zk-SNARKs with Chainlink oracles to securely fetch and verify external data to enable trustless verification of AI models on a blockchain. Our approach addresses the limitations of using unverified external data for AI verification on the blockchain while preserving sensitive information of AI models and enhancing transparency. We demonstrate our methodology with a linear regression model predicting Bitcoin prices using on-chain data verified on the Sepolia testnet. Our results indicate the framework's efficacy, with key metrics including proof generation taking an average of 233.63 seconds and verification time of 61.50 seconds. This research paves the way for transparent and trustless verification processes in blockchain-enabled AI ecosystems, addressing key challenges such as model integrity and model privacy protection. The proposed framework, while exemplified with linear regression, is designed for broader applicability across more complex AI models, setting the stage for future advancements in transparent AI verification.

Problem

• Verifying personalized AI models in decentralized environments
• Ensuring AI model integrity and privacy using zk-SNARKs
• Trustless verification of AI performance claims on blockchain

Innovation

• Uses zk-SNARKs for AI model verification
• Integrates Chainlink oracles for secure data
• Enables trustless blockchain AI verification