Accessible Smart Contracts Verification: Synthesizing Formal Models with Tamed LLMs

2025-01-22

AI Summary

Formal verification of smart contracts faces high modeling barriers and excessive time investment, particularly for non-experts. Method: This paper proposes a three-stage automated modeling approach: (1) code translation to generate formal model stubs; (2) prompt-engineering-driven fine-tuning of large language models (LLMs) to inject precise semantic content; and (3) iterative refinement guided jointly by a syntax validator and semantic equivalence feedback. Contribution/Results: It establishes the first controlled application of LLMs in formal model synthesis, jointly optimizing syntactic correctness and semantic fidelity. Experiments demonstrate substantial reduction in model construction time, enabling non-formal-methods experts to perform high-confidence correctness audits efficiently. The approach significantly lowers the practical barrier to adopting formal verification in smart contract development.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Security and Privacy: Cryptocurrency and smart contracts

Abstract

When blockchain systems are said to be trustless, what this really means is that all the trust is put into software. Thus, there are strong incentives to ensure blockchain software is correct -- vulnerabilities here cost millions and break businesses. One of the most powerful ways of establishing software correctness is by using formal methods. Approaches based on formal methods, however, induce a significant overhead in terms of time and expertise required to successfully employ them. Our work addresses this critical disadvantage by automating the creation of a formal model -- a mathematical abstraction of the software system -- which is often a core task when employing formal methods. We perform model synthesis in three phases: we first transpile the code into model stubs; then we"fill in the blanks"using a large language model (LLM); finally, we iteratively repair the generated model, on both syntactical and semantical level. In this way, we significantly reduce the amount of time necessary to create formal models and increase accessibility of valuable software verification methods that rely on them. The practical context of our work was reducing the time-to-value of using formal models for correctness audits of smart contracts.

Problem

• Formal Model Checking
• Smart Contracts
• Blockchain Software

Innovation

• Large Language Models
• Formal Verification
• Blockchain Smart Contracts