LLM4Security
A list of interesting papers on LLM4security(binary analysis and reverse engineering).
Reverse Engineering
Papers
- (Arxiv pre-pub) LLM4Decompile: Decompiling Binary Code with Large Language Models: A finetuned LLM model for binary decompilation tasks. codes on github: albertan017/LLM4Decompile: Reverse Engineering: Decompiling Binary Code with Large Language Models
- (Arxiv pre-pub) WaDec: Decompiling WebAssembly Using Large Language Model
- (CCS 24) ReSym: Harnessing LLMs to Recover Variable and Data Structure Symbols from Stripped Binaries: A hybrid technique that combines LLMs with program analysis for name&type recovery tasks. ACM CCS 24 accepted paper.
- (Arxiv pre-pub) Exploring the Efficacy of Large Language Models (GPT-4) in Binary Reverse Engineering: This study investigates the capabilities of Large Language Models (LLMs), specifically GPT-4, in the context of Binary Reverse Engineering (RE).
- (Arxiv pre-pub) Self-Constructed Context Decompilation with Fined-grained Alignment Enhancement
- (Arxiv pre-pub) Enhancing Reverse Engineering: Investigating and Benchmarking Large Language Models for Vulnerability Analysis in Decompiled Binaries
- (Arxiv pre-pub) Refining Decompiled C Code with Large Language Models
- (NDSS 24) DeGPT: Optimizing Decompiler Output with LLM
Projects only
- arphanetx/Monocle: Tooling backed by an LLM for performing natural language searches against compiled target binaries. Search for encryption code, password strings, vulnerabilities, etc.
- fr0gger/IATelligence: IATelligence is a Python script that will extract the IAT of a PE file and request GPT to get more information about the API and the ATT&CK matrix related
- moyix/gpt-wpre: Whole-Program Reverse Engineering with GPT-3
- JusticeRage/Gepetto: IDA plugin which queries uses language models to speed up reverse-engineering
-
[G-3PO: A Protocol Droid for Ghidra by Olivia Lucca Fraser Tenable TechBlog Medium](https://medium.com/tenable-techblog/g-3po-a-protocol-droid-for-ghidra-4b46fa72f1ff)