Abstract: Code embedding, an emerging paradigm for source code analysis, has gained significant attention over recent years, particularly in the context of AI-based code analysis. Code embedding aims to represent code semantics through distributed vector representations, which can support a variety of software engineering tasks, including vulnerability detection. This talk will revisit our work on learning-based code analysis, including flow2vec and path-sensitive code embedding, as well as our ongoing and future efforts in this area, built on our open-source SVF framework (SVF GitHub).
Yulei Sui is an ARC Future Fellow and Associate Professor at University of New South Wales (UNSW). His research interests span Software Engineering and Programming Languages, with a particular focus on developing open-source frameworks for static analysis and verification techniques to enhance the reliability and security of modern software systems. His work has been published in top-tier conferences and journals in program analysis and software engineering, and he has received several prestigious Best/Distinguished Paper awards, including at FSE'24, OOPSLA'20, SAS'19, and ICSE'18. In 2023, he was awarded a Google ASPIRE gift grant. He serves as an Associate Editor for IEEE Transactions on Software Engineering and is the Program Chair of LCTES 2024, and a Program Chair for SAS 2025. He is an IEEE Senior Member and a Fellow of Engineers Australia (FIEAust).