5 papers
SyzHarness: Patch-Based Kernel Bug Reproduction with LLM-Synthesized Fuzzing Harnesses
Xingyu Li, Juefei Pu, Haonan Li +4
Automated kernel vulnerability reproduction is essential for bug triage, patch validation, and regression testing, but still lacks an effective and efficient solution. The core cha…
Patch-to-PoC: A Systematic Study of Agentic LLM Systems for Linux Kernel N-Day Reproduction
Juefei Pu, Xingyu Li, Zhengchuan Liang +5
Autonomous large language model (LLM) based systems have recently shown promising results across a range of cybersecurity tasks. However, there is no systematic study on their effe…
TritonForge: Profiling-Guided Framework for Automated Triton Kernel Optimization
Haonan Li, Keyu Man, Partha Kanuparthy +6
High-performance GPU kernel optimization remains a critical yet labor-intensive task in modern machine learning workloads. Although Triton, a domain-specific language for GPU progr…
Rethinking Kernel Program Repair: Benchmarking and Enhancing LLMs with RGym
Kareem Shehada, Yifan Wu, Wyatt D. Feng +4
Large Language Models (LLMs) have revolutionized automated program repair (APR) but current benchmarks like SWE-Bench predominantly focus on userspace applications and overlook the…
LLMBisect: Breaking Barriers in Bug Bisection with A Comparative Analysis Pipeline
Zheng Zhang, Haonan Li, Xingyu Li +2
Bug bisection has been an important security task that aims to understand the range of software versions impacted by a bug, i.e., identifying the commit that introduced the bug. Ho…