Publications

Heajun An, Qi Zhang, Minqian Liu, Xinyi Zhang, Sang Won Lee, Lifu Huang, Pamela J. Wisniewski, and Jin-Hee Cho (2026). "StagePilot: Stage-Level Planning for Long-Horizon Dialogue Simulation in Cybergrooming." arXiv preprint arXiv:2602.05060. [Link]

Heajun An, Connor Ng, Sandesh Sharma Dulal, Junghwan Kim and Jin-Hee Cho (2026). "Grounded but Misleading: Evaluating Semantic Alignment in AI-Generated Security Explanations." arXiv preprint arXiv:2602.05056. [Link]

Heajun An, Qi Zhang, Vedanth Achanta, and Jin-Hee Cho (2026). "CR4T: Rewrite-Based Guardrails for Adolescent LLM Safety." arXiv preprint arXiv:2605.21609. [Link]

Xinyi Zhang, Mamtaj Akter, Heajun An, Minqian Liu, Qi Zhang, Lifu Huang, Jin-Hee Cho, Pamela J. Wisniewski, Sang Won Lee (2026). "From Vulnerable to Resilient: Examining Parent and Teen Perceptions on How to Respond to Unwanted Cybergrooming Advances" Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems (CHI 2026). [Link]

Prakriti Dumaru, Xinyi Zhang, Heajun An, Minqian Liu, Qi Zhang, Lifu Huang, Jin-Hee Cho, Sang Won Lee, Pamela J. Wisniewski (2026). "Dual-Use LLMs in Adolescent Online Safety: From Dangerous Persuaders to Cybergrooming Education." Position Paper, CHI 2026 Workshop: The Developmentally Safe Generative AI Environment for Youth. Available at SSRN 6789698. [Link]

Minqian Liu, Zhiyang Xu, Xinyi Zhang, Heajun An, Sarvech Qadir, Qi Zhang, Pamela J. Wisniewski, Jin-Hee Cho, Sang Won Lee, Ruoxi Jia, and Lifu Huang (2025). "LLM Can Be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Models." Conference on Language Modeling (COLM 2025). [Link]

Heajun An, Marcos Silva, Qi Zhang, Arav Singh, Minqian Liu, Xinyi Zhang, Sarvech Qadir, Sang Won Lee, Lifu Huang, Pamela J. Wisniewski, and Jin-Hee Cho (2025). "Toward Integrated Solutions: A Systematic Interdisciplinary Review of Cybergrooming Research." arXiv preprint arXiv:2503.05727. [Link]