Enhancing Static Analysis for Practical Bug Detection: An LLM-Integrated Approach

While static analysis is instrumental in uncovering software bugs, its precision in analyzing large and intricate codebases remains challenging. The emerging prowess of Large Language Models (LLMs) offers a promising avenue to address these complexities. In this paper, we present LLift, a pioneering...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings of ACM on programming languages Jg. 8; H. OOPSLA1; S. 474 - 499
Hauptverfasser: Li, Haonan, Hao, Yu, Zhai, Yizhuo, Qian, Zhiyun
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York, NY, USA ACM 29.04.2024
Schlagworte:
Automated static analysis
Computing methodologies
Natural language processing
Security and privacy
Software and its engineering
Systems security
large language model
Static analysis
bug detection
ISSN:2475-1421, 2475-1421
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:While static analysis is instrumental in uncovering software bugs, its precision in analyzing large and intricate codebases remains challenging. The emerging prowess of Large Language Models (LLMs) offers a promising avenue to address these complexities. In this paper, we present LLift, a pioneering framework that synergizes static analysis and LLMs, with a spotlight on identifying Use Before Initialization (UBI) bugs within the Linux kernel. Drawing from our insights into variable usage conventions in Linux, we enhance path analysis using post-constraint guidance. This approach, combined with our methodically crafted procedures, empowers LLift to adeptly handle the challenges of bug-specific modeling, extensive codebases, and the unpredictable nature of LLMs. Our real-world evaluations identified four previously undiscovered UBI bugs in the mainstream Linux kernel, which the Linux community has acknowledged. This study reaffirms the potential of marrying static program analysis with LLMs, setting a compelling direction for future research in this area.
ISSN:2475-1421
2475-1421
DOI:10.1145/3649828