吴道远教授

助理教授

BE (NJUPT), MPhil (PolyU), PhD (SMU)

Prof. Daoyuan Wu is currently an Assistant Professor at Lingnan University, where he leads AIS2Lab (Artificial Intelligence and Systems Security Lab). His research focuses on Large Language Models (LLMs) for cybersecurity, AI safety, LLM agents, Web3, and GPU software security. He has published extensively in top-tier venues such as NDSS, USENIX Security, CCS, S&P, ICSE, FSE, ASE, ISSTA, ICLR, and EMNLP, and received a Distinguished Paper Award at NDSS 2025. His recent work, including GPTScan and PropertyGPT, pioneers LLM-driven vulnerability detection and advances semantic reasoning for security automation. Prof. Wu has been the PI for projects funded by Stellar, CCF-Huawei, and several UGC Teaching and Learning grants, and the Co-PI for an RGC CRF project. He also serves as a regular TPC member at top-tier security and AI conferences, as well as a Youth Editorial Board Member of the CCF-B Cybersecurity journal.

Research Interests:

• Large Language Models (LLMs)
• LLMs for Cybersecurity
• AI Safety and Agent Security
• AI infrastructure Security

• Blockchain and Web3 Security