arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.02538cs.CR
收藏

使用机器学习优化模糊测试中的种子输入

Optimizing seed inputs in fuzzing with machine learning

Liang Cheng, Yang Zhang, Yi Zhang, Chen Wu, Zhangtan Li, Yu Fu, Haisheng Li

AI总结:

提出基于机器学习的框架,利用神经网络发现PDF文件与目标程序执行的相关性以生成新种子,显著提升了代码覆盖率与崩溃检测率。

摘要:

模糊测试活动的成功在很大程度上取决于用于测试生成的种子输入的质量。然而,构建一个能够实现对目标程序高代码和行为覆盖率的种子输入语料库是具有挑战性的,特别是当目标程序需要复杂输入格式(如 PDF 文件)时。我们提出了一个基于机器学习的框架,以提高以 PDF 文件作为输入的模糊测试程序的种子输入质量。给定一组初始种子 PDF 文件,我们的框架利用一组神经网络来 1) 发现这些 PDF 文件与目标程序中执行之间的相关性,以及 2) 利用这种相关性生成更有可能探索目标程序中新路径的新种子文件。我们在一组广泛使用的 PDF 查看器上的实验表明,由我们框架生成的改进种子输入能够显著提高目标程序的代码覆盖率以及检测程序崩溃的可能性。

英文摘要:

The success of a fuzzing campaign is heavily depending on the quality of seed inputs used for test generation. It is however challenging to compose a corpus of seed inputs that enable high code and behavior coverage of the target program, especially when the target program requires complex input formats such as PDF files. We present a machine learning based framework to improve the quality of seed inputs for fuzzing programs that take PDF files as input. Given an initial set of seed PDF files, our framework utilizes a set of neural networks to 1) discover the correlation between these PDF files and the execution in the target program, and 2) leverage such correlation to generate new seed files that more likely explore new paths in the target program. Our experiments on a set of widely used PDF viewers demonstrate that the improved seed inputs produced by our framework could significantly increase the code coverage of the target program and the likelihood of detecting program crashes.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑