Abstract:

To address the common issues in the existing compiler fuzzing， such as insufficient test case diversity， high testing costs， and heavy reliance on manual intervention， a multi-strategy compiler fuzzing system based on Large Language Models （LLMs）， DHFUZZ （Deep & Hybrid FUZZer）， was proposed. In the system， multi-strategy test case generation was integrated with LLMs， thereby adjusting prompts to guide the LLM in generating diverse test cases， and the custom code generators were combined to construct test code with specific functions rapidly. Additionally， mutation strategies were incorporated to further enhance test case diversity and improve code coverage， thereby exploring potential compiler execution paths more effectively， so as to trigger deep vulnerabilities. At the same time， an end-to-end automated testing process was designed to fully automate the process from test case generation and compiler execution to bug detection. Experimental results demonstrate that DHFUZZ can generate test cases covering diverse syntactic structures and semantic features， and improves code coverage significantly in tests on mainstream compilers such as GCC （GNU Compiler Collection） and Clang， demonstrating its vulnerability detection potential， and providing an efficient and low-cost automated testing solution for compiler reliability assurance.

Key words: compiler testing, fuzzing, Large Language Model (LLM), test case generation, differential testing

摘要：

针对现有编译器模糊测试中普遍存在的测试用例多样性不足、测试成本高以及人工依赖性强等问题，提出一种基于大语言模型（LLM）的多策略编译器模糊测试系统——DHFUZZ（Deep & Hybrid FUZZer）。该系统融合多策略测试用例生成与LLM，通过调整提示词引导LLM生成多样化测试用例，并结合自定义代码生成器快速构造具备特定功能的测试代码。此外，该系统集成变异策略以进一步丰富测试用例，提升代码覆盖率，从而更有效地探索编译器潜在路径以触发深层漏洞。并且，系统设计端到端的自动化测试流程，以实现从测试用例生成、编译器执行到漏洞检测的全流程自动化。实验结果表明，DHFUZZ能够生成覆盖多种语法结构与语义特征的测试用例，在GCC（GNU Compiler Collection）、Clang等主流编译器测试中显著提高了代码覆盖率，展现出DHFUZZ的漏洞检测潜力，为编译器可靠性保障提供了一种高效、低成本的自动化测试方案。

关键词: 编译器测试, 模糊测试, 大语言模型, 测试用例生成, 差分测试