Wang Zhilong
Xinzhi Luo
In this talk, we will discuss the strengths and limitations of LLMs for code analysis tasks like code search and code clone detection. We will show when the LLMs make mistakes and what kinds of mistakes they make. For example, we observe that the performance of popular LLMs heavily relies on the well-defined variable and function names, therefore, they will make mistakes when some misleading variable name is given. Anyone interested in exploring the intersection of AI and code security analysis can attend this talk.
Wang Zhilong
Security engineer and researcher
Now security engineer in industry.
Ph.D. degree obtained from Penn State University in 2023.
Master degree obtained from Nanjing University in 2019.
Xinzhi Luo
Security Engineer && Researcher
Xinzhi (April) Luo is a Carnegie Mellon University graduate with over three years of experience in information security. She combines technical expertise with a passion for sci-fi, often writing original stories. She is dedicated to innovative cybersecurity solutions.