# Multi-View Decompilation for LLM-Based Malware Classification

arXiv: https://arxiv.org/abs/2606.20436 · HTML: https://mlsanity.com/paper/2606.20436/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 37 references that are in the map.
- First posted on arXiv 18 Jun 2026.

## Builds on (most cited first, 18 of 18)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Mixture-of-Agents Enhances Large Language Model Capabilities](https://mlsanity.com/paper/2406.04692/) (2024)
- [Harnessing Multiple Large Language Models: A Survey on LLM Ensemble](https://mlsanity.com/paper/2502.18036/) (2025)
- [Large Language Models for Code Analysis: Do LLMs Really Do Their Job?](https://mlsanity.com/paper/2310.12357/) (2023)
- [Assessing LLMs in Malicious Code Deobfuscation of Real-world Malware Campaigns](https://mlsanity.com/paper/2404.19715/) (2024)
- [LAMD: Context-driven Android Malware Detection and Classification with LLMs](https://mlsanity.com/paper/2502.13055/) (2025)
- [AppPoet: Large Language Model based Android malware detection via multi-view prompt engineering](https://mlsanity.com/paper/2404.18816/) (2024)
- [Exploring LLMs for Malware Detection: Review, Framework Design, and Countermeasure Approaches](https://mlsanity.com/paper/2409.07587/) (2024)
- [Investigating Large Language Models for Code Vulnerability Detection: An Experimental Study](https://mlsanity.com/paper/2412.18260/) (2024)
- [Boosting Neural Networks to Decompile Optimized Binaries](https://mlsanity.com/paper/2301.00969/) (2023)
- [Exploring the Efficacy of Large Language Models (GPT-4) in Binary Reverse Engineering](https://mlsanity.com/paper/2406.06637/) (2024)
- [Enhancing Reverse Engineering: Investigating and Benchmarking Large Language Models for Vulnerability Analysis in Decompiled Binaries](https://mlsanity.com/paper/2411.04981/) (2024)
- [Feasibility Study for Supporting Static Malware Analysis Using LLM](https://mlsanity.com/paper/2411.14905/) (2024)
- [Exploring Large Language Models for Semantic Analysis and Categorization of Android Malware](https://mlsanity.com/paper/2501.04848/) (2025)
- [Malicious Source Code Detection Using Transformer](https://mlsanity.com/paper/2209.07957/) (2022)
- [Large Language Models for Secure Code Assessment: A Multi-Language Empirical Study](https://mlsanity.com/paper/2408.06428/) (2024)
- [A Decompilation-Driven Framework for Malware Detection with Large Language Models](https://mlsanity.com/paper/2601.09035/) (2026)

## Abstract (arXiv)

Malware analysts often inspect compiled binaries through decompiled pseudo-C, when source code is unavailable. Recent work suggests that large language models (LLMs) can assist this process by classifying decompiled code as benign or malicious, but existing pipelines typically rely on a single decompiler view. We argue that this assumption is fragile: decompilers are lossy heuristic tools, and different decompilers can expose different artefacts of the same binary. We curate a benchmark of benign utilities and malicious programs spanning a range of threat behaviors. Each sample is compiled and decompiled with both Ghidra and RetDec, yielding matched pseudo-C views. Across a range of LLMs from major model families, we find that providing both decompiler views improves malicious-class F1, mainly by increasing recall on malicious samples. Agreement analyses further show that Ghidra and RetDec make partially different errors, supporting the view that decompiler outputs provide complementary evidence. Our results suggest that multi-decompiler prompting is a simple, training-free way to improve LLM-based malware triage in practical settings.