Enhancing Trust in AI Marketplaces: Evaluating On-Chain Verification of Personalized AI models using zk-SNARKs
Nishant Jagannath, Christopher Wong, Braden Mcgrath, Md Farhad Hossain, Asuquo A. Okon, Abbas Jamalipour, Kumudu S. Munasinghe
TL;DR
The paper tackles trust in decentralized AI marketplaces by enabling verifiable, privacy-preserving verification of personalized AI models on the blockchain. It introduces a framework that integrates zk-SNARKs with Chainlink oracles to prove model performance claims without revealing weights or training data, demonstrated on a linear regression model predicting Bitcoin prices using on-chain data. A working implementation on Sepolia shows proof-generation time around 233.63 seconds and verification time around 61.50 seconds, highlighting both feasibility and bottlenecks in proof-arithmetic and setup phases. The work provides a path toward transparent, trustless AI verification in decentralized ecosystems, while acknowledging the need for optimization to scale to more complex models and conducting broader security assessments in future work.
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.