一句话：提出 StateFormer，通过生成式状态建模从二进制中细粒度恢复类型，以替代脆弱的人工推断规则。
二进制类型推断是逆向工程中的关键任务，支撑漏洞分析、二进制加固、取证与反编译等安全应用。该任务十分困难，因为源码级类型信息通常在编译时被剥离，二进制中只剩无类型的内存与寄存器访问。现有方法依赖领域专家手工编写的类型推断规则，这些规则脆弱且维护更新成本高。尽管机器学习方法在自动学习推断规则方面展现出潜力，但其准确率仍然较低，尤其是面对优化后的二进制。为此，作者提出 StateFormer，采用生成式状态建模进行细粒度的二进制类型恢复。摘要未报告具体实验数据与准确率提升幅度。
Binary type inference is a critical reverse engineering task supporting many security applications, including vulnerability analysis, binary hardening, forensics, and decompilation. It is a difficult task because source-level type information is often stripped during compilation, leaving only binaries with untyped memory and register accesses. Existing approaches rely on hand-coded type inference rules defined by domain experts, which are brittle and require nontrivial effort to maintain and update. Even though machine learning approaches have shown promise at automatically learning the inference rules, their accuracy is still low, especially for optimized binaries.
DOI 原文 ·
@inproceedings{paperbot6424,
title = {StateFormer: fine-grained type recovery from binaries using generative state modeling},
author = {Kexin Pei and Jonas Guan and Matthew Broughton and Zhongtian Chen and Songchen Yao and David Williams-King and Vikas Ummadisetty and Junfeng Yang and Baishakhi Ray and Suman Jana},
booktitle = {FSE},
year = {2021},
doi = {10.1145/3468264.3468607}
}