ISC4DGF: Enhancing Directed Grey-box Fuzzing with LLM-Driven Initial Seed Corpus Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Yijiang, Jia, Hongrui, Chen, Liguo, Wang, Xin, Zeng, Zhengran, Wang, Yidong, Gao, Qing, Wang, Jindong, Ye, Wei, Zhang, Shikun, Wu, Zhonghai
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917781888303104
author Xu, Yijiang
Jia, Hongrui
Chen, Liguo
Wang, Xin
Zeng, Zhengran
Wang, Yidong
Gao, Qing
Wang, Jindong
Ye, Wei
Zhang, Shikun
Wu, Zhonghai
author_facet Xu, Yijiang
Jia, Hongrui
Chen, Liguo
Wang, Xin
Zeng, Zhengran
Wang, Yidong
Gao, Qing
Wang, Jindong
Ye, Wei
Zhang, Shikun
Wu, Zhonghai
contents Fuzz testing is crucial for identifying software vulnerabilities, with coverage-guided grey-box fuzzers like AFL and Angora excelling in broad detection. However, as the need for targeted detection grows, directed grey-box fuzzing (DGF) has become essential, focusing on specific vulnerabilities. The initial seed corpus, which consists of carefully selected input samples that the fuzzer uses as a starting point, is fundamental in determining the paths that the fuzzer explores. A well-designed seed corpus can guide the fuzzer more effectively towards critical areas of the code, improving the efficiency and success of the fuzzing process. Even with its importance, many works concentrate on refining guidance mechanisms while paying less attention to optimizing the initial seed corpus. In this paper, we introduce ISC4DGF, a novel approach to generating optimized initial seed corpus for DGF using Large Language Models (LLMs). By leveraging LLMs' deep software understanding and refined user inputs, ISC4DGF creates precise seed corpus that efficiently trigger specific vulnerabilities. Implemented on AFL and tested against state-of-the-art fuzzers like AFLGo, FairFuzz, and Entropic using the Magma benchmark, ISC4DGF achieved a 35.63x speedup and 616.10x fewer target reaches. Moreover, ISC4DGF focused on more effectively detecting target vulnerabilities, enhancing efficiency while operating with reduced code coverage.
format Preprint
id arxiv_https___arxiv_org_abs_2409_14329
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ISC4DGF: Enhancing Directed Grey-box Fuzzing with LLM-Driven Initial Seed Corpus Generation
Xu, Yijiang
Jia, Hongrui
Chen, Liguo
Wang, Xin
Zeng, Zhengran
Wang, Yidong
Gao, Qing
Wang, Jindong
Ye, Wei
Zhang, Shikun
Wu, Zhonghai
Software Engineering
Fuzz testing is crucial for identifying software vulnerabilities, with coverage-guided grey-box fuzzers like AFL and Angora excelling in broad detection. However, as the need for targeted detection grows, directed grey-box fuzzing (DGF) has become essential, focusing on specific vulnerabilities. The initial seed corpus, which consists of carefully selected input samples that the fuzzer uses as a starting point, is fundamental in determining the paths that the fuzzer explores. A well-designed seed corpus can guide the fuzzer more effectively towards critical areas of the code, improving the efficiency and success of the fuzzing process. Even with its importance, many works concentrate on refining guidance mechanisms while paying less attention to optimizing the initial seed corpus. In this paper, we introduce ISC4DGF, a novel approach to generating optimized initial seed corpus for DGF using Large Language Models (LLMs). By leveraging LLMs' deep software understanding and refined user inputs, ISC4DGF creates precise seed corpus that efficiently trigger specific vulnerabilities. Implemented on AFL and tested against state-of-the-art fuzzers like AFLGo, FairFuzz, and Entropic using the Magma benchmark, ISC4DGF achieved a 35.63x speedup and 616.10x fewer target reaches. Moreover, ISC4DGF focused on more effectively detecting target vulnerabilities, enhancing efficiency while operating with reduced code coverage.
title ISC4DGF: Enhancing Directed Grey-box Fuzzing with LLM-Driven Initial Seed Corpus Generation
topic Software Engineering
url https://arxiv.org/abs/2409.14329