ViC:汇编代码搜索只需要虚拟编译器
ViC: Virtual Compiler Is All You Need For Assembly Code Search
AI总结:
针对汇编代码搜索任务高质量数据集构建难的问题,本文通过200亿token数据集继续预训练CodeLlama得到可跨语言虚拟编译的ViC,用其构建大规模数据集使搜索性能超领先基线26%。
摘要:
汇编代码搜索对于减轻逆向工程师的负担至关重要,它使工程师能够在海量二进制程序中使用自然语言快速定位特定函数。尽管该任务意义重大,但构建高质量数据集的诸多复杂性阻碍了其发展。本文探索训练一个大语言模型(LLM)来模拟通用编译器。我们利用Ubuntu软件包编译出一个包含200亿token的数据集,在此基础上对CodeLlama进行继续预训练,得到Virtual Compiler(ViC,虚拟编译器),它能够将任意语言的任意源代码编译为汇编代码。该方法无需真实编译器即可实现跨多种编程语言的虚拟编译,同时保持语义等价性,为汇编代码数据集的构建拓展了可行路径。此外,我们使用ViC构建了一个规模足够大的汇编代码搜索数据集。借助该大规模数据集,我们的汇编代码搜索性能得到了大幅提升,模型表现超越领先基线26%。
英文摘要:
Assembly code search is vital for reducing the burden on reverse engineers, allowing them to quickly identify specific functions using natural language within vast binary programs. Despite its significance, this critical task is impeded by the complexities involved in building high-quality datasets. This paper explores training a Large Language Model (LLM) to emulate a general compiler. By leveraging Ubuntu packages to compile a dataset of 20 billion tokens, we further continue pre-train CodeLlama as a Virtual Compiler (ViC), capable of compiling any source code of any language to assembly code. This approach allows for virtual compilation across a wide range of programming languages without the need for a real compiler, preserving semantic equivalency and expanding the possibilities for assembly code dataset construction. Furthermore, we use ViC to construct a sufficiently large dataset for assembly code search. Employing this extensive dataset, we achieve a substantial improvement in assembly code search performance, with our model surpassing the leading baseline by 26%.
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。