SoK: Potentials and Challenges of Large Language Models for Reverse Engineering
Preprint
Abstract
Reverse Engineering (RE) is central to software security, enabling tasks such as vulnerability discovery and malware analysis, but it remains labor-intensive and requires substantial expertise. Earlier advances in deep learning start to automate parts of RE, particularly for malware detection and vulnerability classification. More recently, a rapidly growing body of work has applied Large Language Models (LLMs) to similar purposes. Their role compared to prior machine learning remains unclear, since some efforts simply adapt existing pipelines with minimal change while others seek to exploit broader reasoning and generative abilities. These differences, combined with varied problem definitions, methods, and evaluation practices, limit comparability, reproducibility, and cumulative progress. This paper systematizes the field by reviewing 44 research papers, including peer-reviewed publications and preprints, and 18 additional open-source projects that apply LLMs in RE. We propose a taxonomy that organizes existing work by objective, target, method, evaluation strategy, and data scale. Our analysis identifies strengths and limitations, highlights reproducibility and evaluation gaps, and examines emerging risks. We conclude with open challenges and future research directions that aim to guide more coherent and security-relevant applications of LLMs in RE.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Large language model (LLM) for software security: Code analysis, malware analysis, reverse engineeringJournal of Information Security and Applications, 2026
- Augmenting Smart Contract Decompiler Output Through Fine-Grained Dependency Analysis and LLM-Facilitated Semantic RecoveryIEEE Transactions on Software Engineering, 2025
- LLM-MalDetect: A Large Language Model-Based Method for Android Malware DetectionIEEE Access, 2025
- llasm: Naming Functions in Binaries by Fusing Encoder-only and Decoder-only LLMsACM Transactions on Software Engineering and Methodology, 2025
- Linear regression combined KNN algorithm to identify latent defects for imbalance data of ICsMicroelectronics Journal, 2022
- SigRec: Automatic Recovery of Function Signatures in Smart ContractsIEEE Transactions on Software Engineering, 2021
- A Strings-Based Similarity Analysis Approach for Characterizing IoT Malware and Inferring Their Underlying RelationshipsIEEE Networking Letters, 2021
- Practical dynamic reconstruction of control flow graphsSoftware: Practice and Experience, 2020
- What’s in a GitHub Star? Understanding Repository Starring Practices in a Social Coding PlatformJournal of Systems and Software, 2018
- Reverse engineering and design recovery: a taxonomyIEEE Software, 1990