LLM-Powered Static Binary Taint Analysis
ACM Transactions on Software Engineering and Methodology · 31.03.2025 · 34 (3) · 1-36
DOI: 10.1145/3711816 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Software Engineering and Methodology, online erschienen am 23.02.2025. Verfasst von Puzhuo Liu und 10 weiteren Autor:innen. Die Arbeit wurde bisher 42-mal zitiert (Crossref) und nennt 103 Literaturangaben. Gefördert von: Ant Group Postdoctoral Programme.
Abstract (Originalsprache)
This article proposes LATTE , the first static binary taint analysis that is powered by a large language model (LLM). LATTE is superior to the state of the art (e.g., Emtaint, Arbiter, Karonte) in three aspects. First, LATTE is fully automated while prior static binary taint analyzers need rely on human expertise to manually customize taint propagation rules and vulnerability inspection rules. Second, LATTE is significantly effective in vulnerability detection, demonstrated by our comprehensive evaluations. For example, LATTE has found 37 new bugs in real-world firmware, which the baselines failed to find. Moreover, 10 of them have been assigned CVE numbers. Lastly, LATTE incurs remarkably low engineering cost, making it a cost-efficient and scalable solution for security researchers and practitioners. We strongly believe that LATTE opens up a new direction to harness the recent advance in LLMs to improve vulnerability analysis for binary programs.
Förderung
- Ant Group Postdoctoral Programme
Zitieren
APA
Liu, P., Sun, C., Zheng, Y., Feng, X., Qin, C., Wang, Y., Xu, Z., Li, Z., Di, P., Jiang, Y., & Sun, L. (2025). LLM-Powered Static Binary Taint Analysis. ACM Transactions on Software Engineering and Methodology, 34(3), 1-36. https://doi.org/10.1145/3711816
Vancouver
Liu P, Sun C, Zheng Y, Feng X, Qin C, Wang Y, et al. LLM-Powered Static Binary Taint Analysis. ACM Transactions on Software Engineering and Methodology. 2025;34(3):1-36. doi:10.1145/3711816
BibTeX
@article{Liu2025,
author = {Liu, Puzhuo and Sun, Chengnian and Zheng, Yaowen and Feng, Xuan and Qin, Chuan and Wang, Yuncheng and Xu, Zhenyang and Li, Zhi and Di, Peng and Jiang, Yu and Sun, Limin},
title = {LLM-Powered Static Binary Taint Analysis},
journal = {ACM Transactions on Software Engineering and Methodology},
year = {2025},
volume = {34},
number = {3},
pages = {1--36},
doi = {10.1145/3711816}
}
EUVIMED