Zixu Gao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Zixu Gao has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Henglong Liang
School of Software Engineering, Sun Yat-sen University, Zhuhai, China
1 shared publication - Peifan Ren
School of Software Engineering, Sun Yat-sen University, Zhuhai, China
1 shared publication - Sicheng Hao
Sun Yat-sen University, Zhuhai, China and Guangdong Engineering Technology Research Center of Blockchain, Zhuhai, China
1 shared publication - Yuhong Nan
Sun Yat-sen University, Zhuhai, China
1 shared publication - Zeqin Liao
Nanyang Technological University, Singapore
1 shared publication - Zibin Zheng
Sun Yat-Sen University, Guangzhou, China
1 shared publication
Latest Publications
- 20 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Software Engineering
- Vol. 51 (12) , 3574-3590
Augmenting Smart Contract Decompiler Output Through Fine-Grained Dependency Analysis and LLM-Facilitated Semantic Recovery
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 function 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, SmartHalo 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 functions shows that SmartHalo significantly improves the quality of the decompiled code, compared to SOTA decompilers (e.g., Gigahorse). Notably, integrating GPT-4o mini with SmartHalo further enhances its performance, achieving a precision of 91.32% and a recall of 87.38% for function boundaries, a precision of 90.40% and a recall of 88.82% for variable types, and a precision of 80.66% and a recall of 91.78% for contract attributes.
- 20 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Software Engineering
- Vol. 51 (12) , 3574-3590
Augmenting Smart Contract Decompiler Output Through Fine-Grained Dependency Analysis and LLM-Facilitated Semantic Recovery
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 function 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, SmartHalo 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 functions shows that SmartHalo significantly improves the quality of the decompiled code, compared to SOTA decompilers (e.g., Gigahorse). Notably, integrating GPT-4o mini with SmartHalo further enhances its performance, achieving a precision of 91.32% and a recall of 87.38% for function boundaries, a precision of 90.40% and a recall of 88.82% for variable types, and a precision of 80.66% and a recall of 91.78% for contract attributes.