Lead R&D on leveraging LLMs for automated smart contract auditing and fuzzing
Research Assistant Professorship
Nanyang Technological University
Conduct pioneering research on AI security at NTU Digital Trust Center
Focus on LLM security and red teaming methodologies
Lead academic initiatives in developing novel threat detection and mitigation techniques
Independent Contractor (Red Teaming Network)
OpenAI
Participate in OpenAI-led red teaming to assess risks and safety profiles
Contributed to evaluation of GPT-4o, DALL-E 3, and Operator
Research Engineer & Penetration Tester
Institute for Infocomm Research (I2R, A*STAR)
Performed penetration testing and research for Singapore government agencies
Education
PhD in Computer Science
Nanyang Technological University
Research on system security, AI security, and penetration testing automation.
Advised by Prof. Tianwei Zhang and Prof. Yang Liu at NTU Cyber Security Lab.
Awarded for PentestGPT: An LLM-empowered Automatic Penetration Testing Tool. Open-source tool with 8k+ GitHub stars demonstrating significant community impact.
Distinguished Paper Award
AISCC Workshop 2024 ∙
February 2024
Awarded for PANDORA: Jailbreak GPTs by Retrieval Augmented Generation Poisoning. Research on RAG security vulnerabilities in LLM systems.