# Augmenting Decompiler Output with Learned Variable Names and Types

arXiv: https://arxiv.org/abs/2108.06363 · HTML: https://mlsanity.com/paper/2108.06363/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Aug 2021.

## Built on by (most cited first, 23 of 23)

- [LLM4Vuln: A Unified Evaluation Framework for Decoupling and Enhancing LLMs' Vulnerability Reasoning](https://mlsanity.com/paper/2401.16185/) (2024)
- [Binary Code Summarization: Benchmarking ChatGPT/GPT-4 and Other Large Language Models](https://mlsanity.com/paper/2312.09601/) (2023)
- [Nova: Generative Language Models for Assembly Code with Hierarchical Attention and Contrastive Learning](https://mlsanity.com/paper/2311.13721/) (2023)
- [Assemblage: Automatic Binary Dataset Construction for Machine Learning](https://mlsanity.com/paper/2405.03991/) (2024)
- [Source Code Foundation Models are Transferable Binary Analysis Knowledge Bases](https://mlsanity.com/paper/2405.19581/) (2024)
- [CodeArt: Better Code Models by Attention Regularization When Symbols Are Lacking](https://mlsanity.com/paper/2402.11842/) (2024)
- [Pre-Training Representations of Binary Code Using Contrastive Learning](https://mlsanity.com/paper/2210.05102/) (2022)
- [Exploring the Limits of ChatGPT in Software Security Applications](https://mlsanity.com/paper/2312.05275/) (2023)
- [BLens: Contrastive Captioning of Binary Functions using Ensemble Embedding](https://mlsanity.com/paper/2409.07889/) (2024)
- [Fast, Fine-Grained Equivalence Checking for Neural Decompilers](https://mlsanity.com/paper/2501.04811/) (2025)
- [Revisiting Deep Learning for Variable Type Recovery](https://mlsanity.com/paper/2304.03854/) (2023)
- [A Deep Dive into Function Inlining and its Security Implications for ML-based Binary Analysis](https://mlsanity.com/paper/2512.14045/) (2025)
- [Fool Me If You Can: On the Robustness of Binary Code Similarity Detection Models against Semantics-preserving Transformations](https://mlsanity.com/paper/2602.12681/) (2026)
- [REBENCH: A Procedural, Fair-by-Construction Benchmark for LLMs on Stripped-Binary Types and Names (Extended Version)](https://mlsanity.com/paper/2604.27319/) (2026)
- [Decaf: Improving Neural Decompilation with Automatic Feedback and Search](https://mlsanity.com/paper/2605.11501/) (2026)
- [REFORGE: A Method for Benchmarking LLMs' Reverse Engineering Capabilities in Decompiled Binary Function Naming](https://mlsanity.com/paper/2607.07738/) (2026)
- [JaxDecompiler: Redefining Gradient-Informed Software Design](https://mlsanity.com/paper/2403.10571/) (2024)
- [Asm2SrcEval: Evaluating Large Language Models for Assembly-to-Source Code Translation](https://mlsanity.com/paper/2512.00134/) (2025)
- [PCodeTrans: Translate Decompiled Pseudocode to Compilable and Executable Equivalent](https://mlsanity.com/paper/2603.14855/) (2026)
- [SoK: AI-Augmented Binary Reversing](https://mlsanity.com/paper/2606.17398/) (2026)
- [Beyond Text Matching: Towards Reference-Free Evaluation for Human-Oriented Binary Reverse Engineering](https://mlsanity.com/paper/2608.07038/) (2026)
- [Reveree: Diagnosing LLM Reverse-Engineering Agents](https://mlsanity.com/paper/2609.01185/) (2026)
- [When LLM Decompilers Recompile More and Preserve Less](https://mlsanity.com/paper/2609.05370/) (2026)

## Abstract (arXiv)

A common tool used by security professionals for reverse-engineering binaries found in the wild is the decompiler. A decompiler attempts to reverse compilation, transforming a binary to a higher-level language such as C. High-level languages ease reasoning about programs by providing useful abstractions such as loops, typed variables, and comments, but these abstractions are lost during compilation. Decompilers are able to deterministically reconstruct structural properties of code, but comments, variable names, and custom variable types are technically impossible to recover. In this paper we present DIRTY (DecompIled variable ReTYper), a novel technique for improving the quality of decompiler output that automatically generates meaningful variable names and types. Empirical evaluation on a novel dataset of C code mined from GitHub shows that DIRTY outperforms prior work approaches by a sizable margin, recovering the original names written by developers 66.4% of the time and the original types 75.8% of the time.