ReSource：面向优化与混淆的变换无关反编译恢复框架
原标题：Decoupling is a Necessity: Transformation-Agnostic Decompiled Code Recovery under Optimization and Obfuscation
AI 摘要
arXiv 论文提出 ReSource，首个多阶段 LLM 反编译框架，旨在从经过优化和混淆的二进制中恢复源码。该框架将二进制到源码的差异分为词汇、句法和语义三层，并分别处理，以应对控制流平坦化等问题。在超过 8 万对函数上，ReSource 实现了 83% 的 Top-5 检索准确率和 0.66 的平均相似度，优于现有基线。
正文节选
Decoupling is a Necessity: Transformation-Agnostic Decompiled Code Recovery under Optimization and Obfuscation Abstract. Reverse engineering is essential for software security analysis and vulnerability detection. Decompilation, the process of lifting binaries to high-level pseudocode, is central to this task. However, production binaries are hostile environments: aggressive compiler optimizations and adversarial obfuscation jointly mangle control structures, obscure variable intents, and disgui