arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2404.09836cs.SEcs.CR
收藏

使用大语言模型进行二进制代码理解我们已经走了多远

How Far Have We Gone in Binary Code Understanding Using Large Language Models

Xiuwei Shang, Shaoyin Cheng, Guoqiang Chen, Yanming Zhang, Li Hu, Xiao Yu, Gangyang Li, Weiming Zhang, Nenghai Yu

AI总结:

本文提出一个涵盖函数名恢复和二进制代码摘要的基准,通过广泛评估现有大语言模型在真实逆向工程场景中的表现,揭示其理解二进制代码的能力与局限,证明LLMs能提升二进制分析效率并具有巨大潜力。

摘要:

二进制代码分析在软件维护、恶意软件检测、软件漏洞发现、补丁分析等多种软件安全应用中发挥着关键作用。然而,与源代码不同,由于缺乏语义信息,逆向工程师理解二进制代码具有挑战性。因此,需要自动化工具来辅助人类解读二进制代码。近年来,两类技术展现出广阔前景:(1)基于深度学习的技术在与二进制代码理解相关的任务中已展示出有竞争力的结果,此外,(2)大语言模型(LLMs)已在源代码层面针对代码理解和生成等任务进行了广泛预训练。这使得参与者想知道LLMs在二进制代码理解方面的能力。在这项工作中,我们提出了一个基准来评估LLMs在真实世界逆向工程场景中的有效性。该基准涵盖两个关键的二进制代码理解任务,包括函数名恢复和二进制代码摘要。通过使用我们的基准对流行的LLMs进行广泛评估,我们对其能力和局限性获得了有价值的见解。我们的评估表明,现有的LLMs能够在一定程度上理解二进制代码,从而提高二进制代码分析的效率。我们的结果凸显了LLMs在推动二进制代码理解领域发展方面的巨大潜力。

英文摘要:

Binary code analysis plays a pivotal role in various software security applications, such as software maintenance, malware detection, software vulnerability discovery, patch analysis, etc. However, unlike source code, understanding binary code is challenging for reverse engineers due to the absence of semantic information. Therefore, automated tools are needed to assist human players in interpreting binary code. In recent years, two groups of technologies have shown promising prospects: (1) Deep learning-based technologies have demonstrated competitive results in tasks related to binary code understanding, furthermore, (2) Large Language Models (LLMs) have been extensively pre-trained at the source-code level for tasks such as code understanding and generation. This makes participants wonder about the ability of LLMs in binary code understanding. In this work, we propose a benchmark to evaluate the effectiveness of LLMs in real-world reverse engineering scenarios. The benchmark covers two key binary code understanding tasks, including function name recovery and binary code summarization. We gain valuable insights into their capabilities and limitations through extensive evaluations of popular LLMs using our benchmark. Our evaluations reveal that existing LLMs can understand binary code to a certain extent, thereby improving the efficiency of binary code analysis. Our results highlight the great potential of the LLMs in advancing the field of binary code understanding.

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。

↑