# Exploring the Efficacy of Large Language Models (GPT-4) in Binary Reverse Engineering

> The paper evaluates GPT-4 for binary reverse engineering through interpretation of human-written and decompiled code, from basic code explanation to malware analysis.

- Authors: Saman Pordanesh; Benjamin Tan
- Venue: arXiv
- Status: Preprint
- Publication / posting date: June 9, 2024
- Date source: First arXiv submission date.
- First arXiv submission: June 9, 2024
- arXiv: 2406.06637
- Reviewed arXiv version: v1
- Sources reviewed: 2026-11-06
- Added to the catalog: 2026-11-06
- Original paper: <https://arxiv.org/abs/2406.06637>
- PDF: <https://arxiv.org/pdf/2406.06637>
- BibTeX: <https://awesomerea.org/papers/citations/paper-gpt4-binary-re.bib>
- Catalog page: <https://awesomerea.org/papers/paper-gpt4-binary-re/>
- Record JSON: <https://awesomerea.org/papers/paper-gpt4-binary-re/record.json>
- Chinese version: [简体中文](https://awesomerea.org/zh/papers/paper-gpt4-binary-re/index.md)

## Scope and limitations

The evaluation covers GPT-4, human-written and decompiled code, basic code interpretation, and more complex malware analysis.

## Why it fits this collection

It directly studies the use of a language model to interpret code in binary reverse engineering.

## Publication and review notes

The date and venue come from the arXiv record.

## Primary sources

1. <https://arxiv.org/abs/2406.06637>

## About this entry

Reviewed against the paper and its primary sources. Cite the original authors using the linked paper or BibTeX.
Original editorial content: MIT. Linked projects, papers and assets retain their own rights and licenses.