一句话：提出 MetaMut 框架，利用大语言模型结合编译器领域知识自动生成语义感知的变异算子，显著提升编译器模糊测试的缺陷发现能力。
变异算子的质量决定了基于变异的模糊测试的搜索空间，但为编译器编写高质量变异算子既需要专家创造力，又要求掌握编译器内部实现知识。本文提出 MetaMut 框架，将编译器领域知识融入提示词与处理流程，以充分利用大语言模型的能力，自动生成语义感知的变异算子。评估中，作者以约每个 0.5 美元的成本、仅需中等人力便构造出 118 个语义感知变异算子，并用其驱动的模糊测试器在 GCC 与 Clang 中发现 131 个缺陷，其中 129 个已被确认或修复。该工作表明，将 AI 引入传统上依赖专家人工干预的软件与系统工程任务是一个有前景的研究方向。
Crafting high-quality mutators-the core of mutation-based fuzzing that shapes the search space-is challenging. It requires human expertise and creativity, and their implementation demands knowledge of compiler internals. This paper presents MetaMut framework for developing new, useful mutators for compiler fuzzing. It integrates our compiler-domain knowledge into prompts and processes that can best harness the capabilities of a large language model. With MetaMut, we have successfully created 118 semantic-aware mutators at approximately $0.5 each, with only moderate human effort. With these mutators, our fuzzer uncovered 131 bugs in GCC and Clang, 129 of which were confirmed or fixed. The success of MetaMut suggests that the integration of AI into software and system engineering tasks traditionally thought to require expert human intervention could be a promising research direction.
@inproceedings{OuL0024,
title = {The Mutators Reloaded: Fuzzing Compilers with Large Language Model Generated Mutation Operators},
author = {Xianfei Ou and Cong Li and Yanyan Jiang and Chang Xu},
booktitle = {ASPLOS},
year = {2024},
doi = {10.1145/3622781.3674171}
}