Towards Large Language Model Guided Kernel Direct Fuzzing
Li, Xie Yuan, Zhaoyue Zhang, Zhenduo Sun, Youcheng Zhang, Lijun
Li, Xie
Yuan, Zhaoyue
Zhang, Zhenduo
Sun, Youcheng
Zhang, Lijun
Author
Supervisor
Department
Computer Science
Embargo End Date
Type
Conference proceeding
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Direct kernel fuzzing is a targeted approach that focuses on specific areas of the kernel, effectively addressing the challenges of frequent updates and the inherent complexity of operating systems, which are critical infrastructure. This paper introduces SyzAgent, a framework integrating LLMs with the state-of-the-art kernel fuzzer Syzkaller, where the LLMs are used to guide the mutation and generation of test cases in real-time. We present preliminary results demonstrating that this method is effective on around 67% cases in our benchmark during the experiment. © The Author(s) 2025.
Co-author(s)
Li X., Yuan Z., Zhang Z., Sun Y., Zhang L.
Citation
X. Li, Z. Yuan, Z. Zhang, Y. Sun, and L. Zhang, “Towards Large Language Model Guided Kernel Direct Fuzzing,” Lecture Notes in Computer Science, vol. 15693, pp. 33–42, Jan. 2025, doi: 10.1007/978-3-031-90900-9_2.
Source
Lecture Notes in Computer Science
Conference
28th International Conference on Fundamental Approaches to Software Engineering, FASE 2025, which was held as part of the International Joint Conferences on Theory and Practice of Software, ETAPS 2025
Keywords
Fuzzing, Large Language Model, Linux Kernel
Subjects
Source
28th International Conference on Fundamental Approaches to Software Engineering, FASE 2025, which was held as part of the International Joint Conferences on Theory and Practice of Software, ETAPS 2025
Publisher
Springer Nature