arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.09157cs.CRcs.LG
收藏

基于深度学习的二进制分析用于x86-64机器代码中的漏洞检测

Deep Learning-based Binary Analysis for Vulnerability Detection in x86-64 Machine Code

Department of Computer Science and Mathematics(计算机科学与数学系);Algoma University(阿尔戈马大学)

Mitchell Petingola

AI总结:

本文提出利用深度学习模型直接分析x86-64机器代码以检测漏洞,发现基于图的模型在漏洞检测中表现更优。

摘要:

尽管当前许多基于深度学习的漏洞检测研究依赖于反汇编二进制文件,本文探讨了从原始x86-64机器代码中提取特征的可行性。虽然汇编语言对人类更易解释,但需要更复杂的模型来捕捉令牌级上下文。相比之下,机器代码可能允许更高效、轻量级的模型,并保留在反汇编中可能丢失的所有信息。本文通过在两种特定深度学习模型架构上的探索性研究来处理漏洞检测任务,并旨在系统评估这些模型在三种漏洞类型上的性能。结果表明,基于图的模型始终优于顺序模型,强调了控制流关系的重要性,并且机器代码包含足够的信息用于有效的漏洞发现。

英文摘要:

While much of the current research in deep learning-based vulnerability detection relies on disassembled binaries, this paper explores the feasibility of extracting features directly from raw x86-64 machine code. Although assembly language is more interpretable for humans, it requires more complex models to capture token-level context. In contrast, machine code may enable more efficient, lightweight models and preserve all information that might be lost in disassembly. This paper approaches the task of vulnerability detection through an exploratory study on two specific deep learning model architectures and aims to systematically evaluate their performance across three vulnerability types. The results demonstrate that graph-based models consistently outperform sequential models, emphasizing the importance of control flow relationships, and that machine code contains sufficient information for effective vulnerability discovery.

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。

↑