Hanjun Luo

Academic Homepage

Hanjun Luo

Ph.D. Student in Computer Science, New York University

I am a first-year Ph.D. student in Computer Science, New York University (Courant Institute of Mathematical Sciences; based at NYU Abu Dhabi). I am currently a Visiting Researcher at Tsinghua University, hosted by Prof. Yipeng Dong. My research focuses on Trustworthy AI and Agentic AI. I am passionate about creating a harmony future of human and AI. I also have long term collaborations with researchers in Nanyang Technology University and Zhejiang University. I am actively looking for research collaborations in LLM safety, trustworthy AI, and human-AI interaction.

Google Scholar GitHub Download CV Email
  • Location Abu Dhabi, UAE
  • Advisor Prof. Hanan Salam
  • Language Chinese (Native), English (Fluent)

Education

  • New York University | Ph.D. in Computer Science (Expected 2030).
  • Zhejiang University | B.E. in Computer Engineering (2025)
  • University of Illinois Urbana-Champaign | B.S. in Computer Engineering (2025)

Recent Work

Publication

Open Full Publications Page

MobileProbe: Adaptive Security Evaluation of Mobile Agents against Trajectory-Aware Injection

NDSS 2027

AtelierEval: Agentic Evaluation of Humans & LLMs as Text-to-Image Prompters

ICML 2026

BiasIG: Benchmarking Multi-dimensional Social Biases in Text-to-Image Models

IJCNN 2026 Oral

AudioStealer: Extracting Audio Prompts via Shapley Value-Guided Query Search

ACL 2026 Findings

Contact

If you are interested in collaboration on Agentic AI and Trustworthy AI, please feel free to reach out.

hl6266@nyu.edu GitHub Profile Download CV Scholar Profile