opML: Optimistic Machine Learning on Blockchain
KD Conway, Cathie So, Xiaohang Yu, Kartin Wong
TL;DR
This work tackles the challenge of performing trustworthy, scalable machine learning on the blockchain by moving away from costly zero-knowledge proofs toward an optimistic, fraud-proof paradigm (opML). It introduces a Fra ud Proof Virtual Machine (FPVM), a semi-native, multi-phase dispute protocol, and a high-performance ML engine to enable on-chain inference for large models (e.g., 7B-LLaMA) using CPU resources. Under the AnyTrust security model, opML achieves safety and liveness with low on-chain proof costs, and utilizes an attention-based incentive mechanism to mitigate the verifier dilemma. The framework also outlines extensions to training and privacy, including hybrid zkML/opML configurations and zkVM-assisted multi-step verification, positioning opML as a practical pathway to decentralized, transparent AI services on-chain.
Abstract
The integration of machine learning with blockchain technology has witnessed increasing interest, driven by the vision of decentralized, secure, and transparent AI services. In this context, we introduce opML (Optimistic Machine Learning on chain), an innovative approach that empowers blockchain systems to conduct AI model inference. opML lies a interactive fraud proof protocol, reminiscent of the optimistic rollup systems. This mechanism ensures decentralized and verifiable consensus for ML services, enhancing trust and transparency. Unlike zkML (Zero-Knowledge Machine Learning), opML offers cost-efficient and highly efficient ML services, with minimal participation requirements. Remarkably, opML enables the execution of extensive language models, such as 7B-LLaMA, on standard PCs without GPUs, significantly expanding accessibility. By combining the capabilities of blockchain and AI through opML, we embark on a transformative journey toward accessible, secure, and efficient on-chain machine learning.