Proj. CAR Paper Reading: Augmenting Decompiler Output with Learned Variable Names and Types

Posted 雪溯

tags:

篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了Proj. CAR Paper Reading: Augmenting Decompiler Output with Learned Variable Names and Types相关的知识,希望对你有一定的参考价值。

Abstract

背景:

  1. decompilers难以恢复注释、variable names, custom variable types

本文:
工具:DIRTY((DecompIled variable ReTYper)
方法: postprocesses decompiled files
基于: Transformer
训练数据:Github

效果:
实验:

  1. outperforms prior work approaches by a sizable margin
  2. recovering the original names written by developers 66.4% of the time and the original types 75.8% of the time.

以上是关于Proj. CAR Paper Reading: Augmenting Decompiler Output with Learned Variable Names and Types的主要内容,如果未能解决你的问题,请参考以下文章

Paper Reading

Testing & Paper reading——Sketchvisor

CVPR 2016 paper reading

Paper Reading_Computer Architecture

Paper Reading_SysML

paper reading:gaze tracking