# Revisiting Deep Learning for Variable Type Recovery

arXiv: https://arxiv.org/abs/2304.03854 · HTML: https://mlsanity.com/paper/2304.03854/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 18 references that are in the map.
- First posted on arXiv 7 Apr 2023.

## Builds on (most cited first, 5 of 5)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [DIRE: A Neural Approach to Decompiled Identifier Naming](https://mlsanity.com/paper/1909.09029/) (2019)
- [Augmenting Decompiler Output with Learned Variable Names and Types](https://mlsanity.com/paper/2108.06363/) (2021)
- [MIMOSA: Reducing Malware Analysis Overhead with Coverings](https://mlsanity.com/paper/2101.07328/) (2021)

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

- [Context-Guided Decompilation: A Step Towards Re-executability](https://mlsanity.com/paper/2511.01763/) (2025)

## Abstract (arXiv)

Compiled binary executables are often the only available artifact in reverse engineering, malware analysis, and software systems maintenance. Unfortunately, the lack of semantic information like variable types makes comprehending binaries difficult. In efforts to improve the comprehensibility of binaries, researchers have recently used machine learning techniques to predict semantic information contained in the original source code. Chen et al. implemented DIRTY, a Transformer-based Encoder-Decoder architecture capable of augmenting decompiled code with variable names and types by leveraging decompiler output tokens and variable size information. Chen et al. were able to demonstrate a substantial increase in name and type extraction accuracy on Hex-Rays decompiler outputs compared to existing static analysis and AI-based techniques. We extend the original DIRTY results by re-training the DIRTY model on a dataset produced by the open-source Ghidra decompiler. Although Chen et al. concluded that Ghidra was not a suitable decompiler candidate due to its difficulty in parsing and incorporating DWARF symbols during analysis, we demonstrate that straightforward parsing of variable data generated by Ghidra results in similar retyping performance. We hope this work inspires further interest and adoption of the Ghidra decompiler for use in research projects.