Code Analysis
Code analysis research focuses on automatically understanding and evaluating software code, aiming to improve software quality, security, and development efficiency. Current efforts leverage large language models (LLMs) like GPT and CodeBERT, along with techniques such as contrastive learning and graph neural networks, to analyze code structure, semantics, and behavior, often incorporating Abstract Syntax Trees (ASTs) and other code representations. These advancements enable automated tasks such as vulnerability detection, performance optimization, and maintainability assessment, impacting software engineering practices and security through improved tools and methodologies.
Papers
Follow-up Attention: An Empirical Study of Developer and Neural Model Code Exploration
Matteo Paltenghi, Rahul Pandita, Austin Z. Henley, Albert Ziegler
Pre-Training Representations of Binary Code Using Contrastive Learning
Yifan Zhang, Chen Huang, Yueke Zhang, Kevin Cao, Scott Thomas Andersen, Huajie Shao, Kevin Leach, Yu Huang