Augmenting Smart Contract Decompiler Output through Fine-grained Dependency Analysis and LLM-facilitated Semantic Recovery

TL;DR

SmartHalo enhances smart contract decompiler outputs by combining static analysis and large language models, significantly improving accuracy in reconstructing source code features like method boundaries and variable types.

Contribution

The paper introduces SmartHalo, a novel framework that integrates static analysis with LLMs to improve decompiler accuracy for Solidity smart contracts.

Findings

Achieves 87.39% precision in method boundary detection.

Reaches 90.39% accuracy in variable type recovery.

Improves overall decompilation quality compared to state-of-the-art tools.

Abstract

Decompiler is a specialized type of reverse engineering tool extensively employed in program analysis tasks, particularly in program comprehension and vulnerability detection. However, current Solidity smart contract decompilers face significant limitations in reconstructing the original source code. In particular, the bottleneck of SOTA decompilers lies in inaccurate method identification, incorrect variable type recovery, and missing contract attributes. These deficiencies hinder downstream tasks and understanding of the program logic. To address these challenges, we propose SmartHalo, a new framework that enhances decompiler output by combining static analysis (SA) and large language models (LLM). SmartHalo leverages the complementary strengths of SA's accuracy in control and data flow analysis and LLM's capability in semantic prediction. More specifically, \system{} constructs a new data structure - Dependency Graph (DG), to extract semantic dependencies via static analysis. Then, it takes DG to create prompts for LLM optimization. Finally, the correctness of LLM outputs is validated through symbolic execution and formal verification. Evaluation on a dataset consisting of 465 randomly selected smart contract methods shows that SmartHalo significantly improves the quality of the decompiled code, compared to SOTA decompilers (e.g., Gigahorse). Notably, integrating GPT-4o with SmartHalo further enhances its performance, achieving precision rates of 87.39% for method boundaries, 90.39% for variable types, and 80.65% for contract attributes.