Gelei Deng

Ph.D. Candidate, AI Engineer, OpenAI Red Team Member

Nanyang Technological University

Biography

I am a fourth-year Ph.D. candidate at Nanyang Technological University, advised by Prof. Tianwei Zhang and Prof. Yang Liu. I’m also working for Quantstamp as an AI engineer and blockchain auditor, and I’m a member of the OpenAI Red Team.

My current research interests cover a wide ranges in cyber security domain, including system security, web security, security testing, blockchain security and AI security. I’m particularly interested in AI for Security (leveraging AI for security-related tasks) and AI Safety/Security.

Interests

System Security
Large Language Model Security
Security Testing

Education

PhD in Computer Science, 2020-2024
Nanyang Technological University

Highlighted Projects

PentestGPT

The first LLM-empowered automatic penetration testing tool, with 6k+ stars on GitHub and active community.

Recent Publications

Quickly discover relevant content by filtering publications.

Gelei Deng, Yi Liu, Yuekang Li, Kailong Wang, Ying Zhang, Zefeng Li, Haoyu Wang, Tianwei Zhang, Yang Liu (2024). MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots. In NDSS 2024.

Gelei Deng, Yi Liu, Kailong Wang, Yuekang Li, Tianwei Zhang, Yang Liu (2024). PANDORA: Jailbreak GPTs by Retrieval Augmented Generation Poisoning. AISCC 2024.

Yi Liu, Yuekang Li, Gelei Deng, Felix Juefei-Xu, Yao Du, Cen Zhang, Chengwei Liu, Yeting Li, Lei Ma, Yang Liu (2023). ASTER: Automatic Speech Recognition System Accessibility Testing for Stutterers. ASE 2023.

Yi Liu, Gelei Deng, Zhengzi Xu, Yuekang Li, Yaowen Zheng, Ying Zhang, Lida Zhao, Tianwei Zhang, Yang Liu (2023). Jailbreaking chatgpt via prompt engineering: An empirical study. pre-print.

Gelei Deng, Zhiyi Zhang, Yuekang Li, Yi Liu, Tianwei Zhang, Yang Liu, Guo Yu, Dongjin Wang (2023). NAUTILUS: Automated RESTful API Vulnerability Detection. In USENIX Security 2023.

See all publications