Page 26 - 《软件学报》2026年第6期

李玉璋 等: BinDec: 面向 RISC-V 的 LLM 与符号执行协同反编译方法 2345

[24] Armengol-Estapé J, Woodruff J, Cummins C, O’Boyle MFP. SLaDe: A portable small language model decompiler for optimized
assembly. In: Proc. of the 2024 IEEE/ACM Int’l Symp. on Code Generation and Optimization (CGO). Edinburgh: IEEE, 2024. 67–80.
[doi: 10.1109/CGO57630.2024.10444788]
[25] Melo LTC, Ribeiro RG, Guimarães BCF, Pereira FMQ. Type inference for C: Applications to the static analysis of incomplete programs.
ACM Trans. on Programming Languages and Systems, 2020, 42(3): 15. [doi: 10.1145/3421472]
[26] Jiang N, Wang CX, Liu K, Xu XZ, Tan L, Zhang XY, Babkin P. Nova: Generative language models for assembly code with hierarchical
attention and contrastive learning. In: Proc. of the 13th Int’l Conf. on Learning Representations. Singapore: OpenReview.net, 2025.
[27] Xu XZ, Zhang Z, Su ZA, Huang ZY, Feng SW, Ye YP, Jiang N, Xie DN, Cheng SY, Tan L, Zhang XY. Unleashing the power of
generative model in recovering variable names from stripped binary. In: Proc. of the 32nd Annual Network and Distributed System
Security Symp. San Diego: The Internet Society, 2025. 1–18. [doi: 10.14722/ndss.2025.240276]
[28] Wong WK, Wu DY, Wang HJ, Li ZJ, Liu ZB, Wang S, Tang QY, Nie S, Wu S. DecLLM: LLM-augmented recompilable decompilation
for enabling programmatic use of decompiled code. Proc. of the ACM on Software Engineering, 2025, 2(ISSTA): ISSTA081. [doi: 10.
1145/3728958]
[29] Hu PW, Liang RG, Chen K. DeGPT: Optimizing decompiler output with LLM. In: Proc. of the 31st Annual Network and Distributed
System Security Symp. San Diego: The Internet Society, 2024. 1–16. [doi: 10.14722/ndss.2024.24401]
[30] Glock J, Pichler J, Pinzger M. PASDA: A partition-based semantic differencing approach with best effort classification of undecided
cases. Journal of Systems and Software, 2024, 213: 112037. [doi: 10.1016/j.jss.2024.112037]
[31] Ramos DA, Engler D. Under-constrained symbolic execution: Correctness checking for real code. In: Proc. of the 24th USENIX Security
Symp. Washington: USENIX Association, 2015. 49–64.
[32] Armengol-Estapé J, Woodruff J, Brauckmann A, de Souza Magalhães JW, O’Boyle MFP. ExeBench: An ML-scale dataset of executable
C functions. In: Proc. of the 6th ACM SIGPLAN Int’l Symp. on Machine Programming. San Diego: ACM, 2022. 50–59. [doi: 10.1145/
3520312.3534867]
[33] Papineni K, Roukos S, Ward T, Zhu WJ. BLEU: A method for automatic evaluation of machine translation. In: Proc. of the 40th Annual
Meeting of the Association for Computational Linguistics. Philadelphia: ACL, 2002. 311–318. [doi: 10.3115/1073083.1073135]
[34] Cadar C, Dunbar D, Engler D. KLEE: Unassisted and automatic generation of high-coverage tests for complex systems programs. In:
Proc. of the 8th USENIX Symp. on Operating Systems Design and Implementation. San Diego: USENIX Association, 2008. 209–224.
[doi: 10.5555/1855741.1855756]
[35] David R, Bardin S, Ta TD, Mounier L, Feist J, Potet ML, Marion JY. BINSEC/SE: A dynamic symbolic execution toolkit for binary-level
analysis. In: Proc. of the 23rd Int’l Conf. on Software Analysis, Evolution, and Reengineering (SANER). Osaka: IEEE, 2016. 653–656.
[doi: 10.1109/SANER.2016.43]
[36] Tempel S, Brandt T, Lüth C, Dietrich C, Drechsler R. Accurate and extensible symbolic execution of binary code based on formal ISA
semantics. In: Proc. of the 2025 Design, Automation & Test in Europe Conf. (DATE). Lyon: IEEE, 2025. 1–7. [doi: 10.23919/
DATE64628.2025.10993257]

作者简介
李玉璋, 博士生, CCF 学生会员, 主要研究领域为自动软件工程, 软件供应链安全.
张熙, 博士, 教授, 博士生导师, CCF 专业会员, 主要研究领域为大数据分析, 网络内容安全, 可信人工智能.
徐涛, 博士, 高级工程师, 主要研究领域为计算机系统结构, 系统安全.