VeriStruct: AI-assisted Automated Verification of Data-Structure Modules in Verus

TL;DR

VeriStruct is an AI-assisted framework that automates the verification of complex data structure modules in Verus, improving accuracy through syntax guidance and repair, and demonstrating high success rates on Rust modules.

Contribution

It extends AI-assisted verification from functions to data structures, introducing a planner, syntax guidance, and repair mechanisms for better accuracy.

Findings

Succeeded on 10 out of 11 modules

Verified 128 out of 129 functions (99.2%)

Effective in automating complex data structure verification

Abstract

We introduce VeriStruct, a novel framework that extends AI-assisted automated verification from single functions to more complex data structure modules in Verus. VeriStruct employs a planner module to orchestrate the systematic generation of abstractions, type invariants, specifications, and proof code. To address the challenge that LLMs often misunderstand Verus' annotation syntax and verification-specific semantics, VeriStruct embeds syntax guidance within prompts and includes a repair stage to automatically correct annotation errors. In an evaluation on eleven Rust data structure modules, VeriStruct succeeds on ten of the eleven, successfully verifying 128 out of 129 functions (99.2%) in total. These results represent an important step toward the goal of automatic AI-assisted formal verification.