Harnessing the Power of LLM to Support Binary Taint Analysis

Authors: Puzhuo Liu, Chengnian Sun, Yaowen Zheng, Xuan Feng, Chuan Qin, Yuncheng Wang, Zhenyang Xu, Zhi Li, Peng Di, Yu Jiang, Limin Sun
Published: 2023-10-12 | Updated: 2025-01-09

Source: https://arxiv.org/abs/2310.08275

PDF: https://arxiv.org/pdf/2310.08275

Labels Predicted by AI

セキュリティ分析 動的分析 プロンプティング戦略

Please note that these labels were automatically added by AI. Therefore, they may not be entirely accurate.
For more details, please see the About the Literature Database page.

Abstract

This paper 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, and 7 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.