本文已被：浏览 1115次 下载 1601次
Received:October 09, 2020 Revised:November 02, 2020
Received:October 09, 2020 Revised:November 02, 2020
中文摘要: 模糊测试作为一种自动化检测应用程序漏洞的方法, 常常被用来检测各种软件以及计算机系统的漏洞挖掘中. 而种子文件质量的高低对于模糊测试的效果而言至关重要. 所以本文提出了一种基于机器学习的模糊测试种子输入的生成方法, 利用样本输入和基于机器学习的技术来学习样本输入的规则和语法. 并利用学到的规则和语法来生成全新的种子输入. 我们还提出了一个采样方法. 使得这些新的种子输入的覆盖率较之前有了明显提升.
中文关键词: 模糊测试 机器学习 代码覆盖率 种子生成 Transformer模型 attention机制
Abstract:As a method of automatically detecting application vulnerabilities, fuzzing often serves for various software and computer systems. The quality of the seed file is very important to the fuzzing test. Therefore, this study proposes a method for generating fuzzing seed input based on machine learning. It relies on sample input and machine learning-based technology to learn the rules and grammar of sample input, which are then used to generate new seed input. We also propose a sampling method, considerably improving the coverage of the new seed input.
keywords: fuzzing machine learning code coverage seed generation Transformer model attention mechanism
文章编号： 中图分类号： 文献标志码：
基金项目:国家自然科学基金(61471344, 61772506, 62072448); 国家重点研发计划(2017YFB0802902)
引用文本：
王敏,冯登国,程亮,张阳.基于机器学习的模糊测试种子输入优化.计算机系统应用,2021,30(6):1-8
WANG Min,FENG Deng-Guo,CHENG Liang,ZHANG Yang.Optimization of Fuzzing Seed Input Based on Machine Learning.COMPUTER SYSTEMS APPLICATIONS,2021,30(6):1-8
王敏,冯登国,程亮,张阳.基于机器学习的模糊测试种子输入优化.计算机系统应用,2021,30(6):1-8
WANG Min,FENG Deng-Guo,CHENG Liang,ZHANG Yang.Optimization of Fuzzing Seed Input Based on Machine Learning.COMPUTER SYSTEMS APPLICATIONS,2021,30(6):1-8
