The rapid advancement of Large Language Models (LLMs) has opened new opportunities for static bug and vulnerability detection, offering complementary insights to traditional static analysis. In this talk, I will present our recent work on LLM-based static bug detection, highlighting how LLMs can extend the knowledge boundary of static analysis to achieve higher precision and recall in bug detection. Moreover, I will also discuss the promise and the limitations of LLMs in practical vulnerability detection.
Speaker info: “Yiling Lou is a pre-tenure associate professor at Fudan University. Previously, she was a postdoctoral researcher at Purdue University and she received her Ph.D. from Peking University. Her research interests lie in the intersection between software engineering and artificial intelligence, with a focus on building AI-powered systems to support software development and maintenance. Her work has received two ACM SIGSOFT Distinguished Paper Awards (ISSTA 2019 and FSE 2023) and one IEEE TCSE Distinguished Paper Award (ICSME 2021). She served as the PC co-chair for AIware 2025 and LLM4Code 2024/2025.”