Hui Shu

A Systematic Evaluation of Large Language Models in API Mapping

2026 · IEICE Transactions on Information and Systems

API mapping is a critical step in code migration. Traditional approaches often rely on manually crafted rules or task-specific supervised data, which can be inefficient and exhibit poor generalization capabilities. Recently, Large Language Models (LLMs) …

FunSp: countering binary code similarity detection through function splitting

2026 · The Computer Journal

Abstract Binary code similarity detection (BCSD) poses a significant threat to software security by enabling reverse engineers to identify critical functions in binaries. Code obfuscation is a primary defense, yet existing techniques often incur high …

<tt>SemAder</tt> : Evading LLM-Based Binary Code Analysis via Structure-Semantics Joint Induction

2026 · ACM Transactions on Privacy and Security

With the rapid advancement of artificial intelligence (AI), particularly the widespread adoption of large language models (LLMs) in code comprehension and analysis, their strong semantic parsing capabilities have introduced new threats to software security. Attackers …