Large Language Model assisted Hybrid Fuzzing

TL;DR

This paper introduces HyllFuzz, a hybrid fuzzing approach that leverages Large Language Models to improve code coverage and bug detection efficiency in software testing.

Contribution

It develops an LLM-empowered concolic execution method that enhances hybrid fuzzing by generating inputs to reach complex program branches more effectively.

Findings

HyllFuzz covers 31.43% to 59.48% more code branches than state-of-the-art tools.

LLM-based concolic execution is 3 to 19 times faster than traditional methods.

HyllFuzz discovered seven previously unknown bugs in real-world software.

Abstract

Greybox fuzzing is one of the most popular methods for detecting software vulnerabilities, which conducts a biased random search within the program input space. To enhance its effectiveness in achieving deep coverage of program behaviors, greybox fuzzing is often combined with concolic execution, which performs a path-sensitive search over the domain of program inputs. In hybrid fuzzing, conventional greybox fuzzing is followed by concolic execution in an iterative loop, where reachability roadblocks encountered by greybox fuzzing are tackled by concolic execution. However, such hybrid fuzzing still suffers from difficulties conventionally faced by concolic execution, such as the need for environment modeling and system call support. In this work, we explore the potential of developing "smart" concolic execution empowered by Large Language Models (LLMs), leveraging their knowledge of code semantics during constraint computing and solving. When coverage-based greybox fuzzing reaches a roadblock in terms of reaching certain branches, we conduct a slicing on the execution trace and suggest modifications of the input to reach the relevant branches. The LLM is used as a solver to generate the modified input to reach the desired branches. Compared with state-of-the-art hybrid fuzzers CoFuzz, Intriguer, and QSYM, our LLM-based hybrid fuzzer HyllFuzz(pronounced "hill fuzz") covers 31.43%, 44.56%, and 59.48% more code branches, respectively. Furthermore, the LLM-based concolic execution in HyllFuzz takes a time that is 3--19 times faster than the concolic execution running in existing hybrid fuzzing tools. In extensively tested real-world subjects, HyllFuzz exposed seven previously unknown bugs. This experience shows that LLMs can be effectively inserted into the iterative loop of hybrid fuzzers to efficiently expose more program behaviors.