# Improving type information inferred by decompilers with supervised machine learning

arXiv: https://arxiv.org/abs/2101.08116 · HTML: https://mlsanity.com/paper/2101.08116/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 64 references that are in the map.
- First posted on arXiv 19 Jan 2021.

## Builds on (most cited first, 4 of 4)

- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Macro F1 and Macro F1](https://mlsanity.com/paper/1911.03347/) (2019)
- [Towards Neural Decompilation](https://mlsanity.com/paper/1905.08325/) (2019)
- [Malware Detection using Machine Learning and Deep Learning](https://mlsanity.com/paper/1904.02441/) (2019)

## Built on by (most cited first, 1 of 1)

- [How Different Tokenization Algorithms Impact LLMs and Transformer Models for Binary Code Analysis](https://mlsanity.com/paper/2511.03825/) (2025)

## Abstract (arXiv)

In software reverse engineering, decompilation is the process of recovering source code from binary files. Decompilers are used when it is necessary to understand or analyze software for which the source code is not available. Although existing decompilers commonly obtain source code with the same behavior as the binaries, that source code is usually hard to interpret and certainly differs from the original code written by the programmer. Massive codebases could be used to build supervised machine learning models aimed at improving existing decompilers. In this article, we build different classification models capable of inferring the high-level type returned by functions, with significantly higher accuracy than existing decompilers. We automatically instrument C source code to allow the association of binary patterns with their corresponding high-level constructs. A dataset is created with a collection of real open-source applications plus a huge number of synthetic programs. Our system is able to predict function return types with a 79.1% F1-measure, whereas the best decompiler obtains a 30% F1-measure. Moreover, we document the binary patterns used by our classifier to allow their addition in the implementation of existing decompilers.