lt-asset/resymPara o nosso artigo da CCS24 🏆 "ReSym: Harnessing LLMs to Recover Variable and Data Structure Symbols from Stripped Binaries" de Danning Xie, Zhuo Zhang, Nan Jiang, Xiangzhe Xu, Lin Tan e Xiangyu Zhang. 🏆 Vencedor do Prêmio de Artigo Distinto ACM SIGSAC
Este repositório fornece artefatos para o artigo "ReSym: Harnessing LLMs to Recover Variable and Data Structure Symbols from Stripped Binaries" (CCS 2024).
🏆 Vencedor do Prêmio ACM SIGSAC de Artigo Destaque
Nota: Estamos mantendo/atualizando ativamente nossos artefatos. Certifique-se de usar a versão mais recente.
process_data. Ele gera dados de treinamento com informações de símbolos ground truth. O script é push-button, e as instruções de uso são fornecidas na pasta.ReSym_rawdata). Isso inclui arquivos binários brutos e o código descompilado correspondente que usamos neste projeto:
bin/: Contém arquivos binários não-strippados brutos com informações de depuração.decompiled/: Código descompilado de binários totalmente strippados.metadata.json: Metadados dos binários, incluindo informações do projeto.training_src para os modelos VarDecoder e FieldDecoder.ReSym_data). Isso inclui: dados de treinamento, dados de teste e resultados de previsão para FieldDecoder e VarDecoder.posterior_reasoning. Os detalhes e as instruções podem ser encontrados na pasta.training_src.@inproceedings{10.1145/3658644.3670340,
author = {Xie, Danning and Zhang, Zhuo and Jiang, Nan and Xu, Xiangzhe and Tan, Lin and Zhang, Xiangyu},
title = {ReSym: Harnessing LLMs to Recover Variable and Data Structure Symbols from Stripped Binaries},
year = {2024},
isbn = {9798400706363},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3658644.3670340},
doi = {10.1145/3658644.3670340},
abstract = {Decompilation aims to recover a binary executable to the source code form and hence has a wide range of applications in cyber security, such as malware analysis and legacy code hardening. A prominent challenge is to recover variable symbols, including both primitive and complex types such as user-defined data structures, along with their symbol information such as names and types. Existing efforts focus on solving parts of the problem, e.g., recovering only types (without names) or only local variables (without user-defined structures). In this paper, we propose ReSym, a novel hybrid technique that combines Large Language Models (LLMs) and program analysis to recover both names and types for local variables and user-defined data structures. Our method encompasses fine-tuning two LLMs to handle local variables and structures, respectively. To overcome the token limitations inherent in current LLMs, we devise a novel Prolog-based algorithm to aggregate and cross-check results from multiple LLM queries, suppressing uncertainty and hallucinations. Our experiments show that ReSym is effective in recovering variable information and user-defined data structures, substantially outperforming the state-of-the-art methods.},
booktitle = {Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security},
pages = {4554–4568},
numpages = {15},
keywords = {large language models, program analysis, reverse engineering},
location = {Salt Lake City, UT, USA},
series = {CCS '24}
}