研究人员开发了一种新颖的方法，通过整合逆向工程技术和大型语言模型（LLM）推理，从剥离的二进制函数中恢复源代码。该方法侧重于从数据库中检索实际的源代码片段，而不是生成伪代码。该系统提取字符串和函数名等关键锚点，使用倒排索引搜索查找候选源文件，然后利用LLM根据汇编、反编译代码和元数据对这些候选文件进行重新排序。在剥离的tcpdump二进制文件的高保真数据库上进行的评估中，该方法实现了95.2%的汇编指令覆盖率，证明了其在高数据质量环境中的有效性。 AI
影响 这项研究通过从二进制文件中恢复源代码，可能有助于提高理解和分析软件的能力，从而促进安全分析和逆向工程工作。
排序理由 详细介绍新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2607.07738v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly applied to reverse-engineering tasks, and recent threat-intelligence reporting shows them operating inside live offensive-security workflows. Claims about their capability, however, ou…
arXiv:2607.09452v1 Announce Type: cross Abstract: We present a practical pipeline for recovering source code from stripped binary functions by combining reverse engineering, anchor-based source code retrieval, and large language model reasoning. Our binary-to-source-code retrieva…
We present a practical pipeline for recovering source code from stripped binary functions by combining reverse engineering, anchor-based source code retrieval, and large language model reasoning. Our binary-to-source-code retrieval method attempts to identify the source function …