Education

• Ph.D in Computer Science, Virginia Tech, 2026 (expected)
• M.S. in Computer Science, New York University, 2021
• B.S. in Electronic Science and Technology, Beijing Institute of Technology, 2019

Research Projects

• Strategic and Stage-Structured LLM Dialogue Systems
  • Funding: National Science Foundation (NSF)
  • Date: Sep. 2024 – Present
  • Principal Investigators: Jin-Hee Cho, Pamela J. Wisniewski, Lifu Huang, Sang Won Lee
  • Website: Link
  • Investigate how large language models can conduct structured, goal-directed, and long-horizon conversations in socially sensitive domains.
  • Developed DeepSAGE, a hybrid LLM–Deep Reinforcement Learning framework that models an initial Cognitive Behavioral Therapy session as eleven stages with explicit therapeutic objectives.
  • Contributed to StagePilot, an offline reinforcement learning framework for stage-controlled cybergrooming dialogue simulation.
• Detection, Explanation, and Mitigation of AI Failures
  • Funding: National Science Foundation (NSF)
  • Date: Aug. 2025 – Present
  • Principal Investigators: Jin-Hee Cho
  • Website: Link
  • Study trustworthy AI from an instance-level perspective, focusing on detecting, explaining, prioritizing, and mitigating individual model failures after deployment.
  • Developed X-MAP, an explainable misclassification-analysis framework that transforms local SHAP attributions into semantic topic profiles using non-negative matrix factorization.
• Uncertainty-Aware Reinforcement Learning for Competitive Influence Maximization
  • Funding: National Science Foundation (NSF)
  • Date: Oct. 2021 – Aug. 2025
  • Principal Investigators: Jin-Hee Cho, Feng Chen, Dong Hyun Jeong
  • Website: Link
  • Investigated competitive influence maximization under uncertain, evolving, and non-binary user opinions.
  • Developed DRIM, a dual-agent Deep Reinforcement Learning framework for modeling strategic competition between parties propagating true and false information in online social networks.

Teaching Experience

• Virginia Tech (Teaching Assistant)
  • CS 5584: Network Security — Fall 2026
  • CS 2104: Introduction to Problem Solving in Computer Science — Spring 2022, Summer 2024
  • CS 3114: Data Structures and Algorithms — Fall 2021
• New York University (Teaching Assistant)
  • CS-GY 6823: Network Security — Spring 2021

Professional Service

• Organizing Chair
  • NSF Artificial Intelligence Awareness Workshop — Sep. 2025
• Program Committee
  • AAAI Conference on Artificial Intelligence (AAAI 2027)
  • IEEE International Conference on Web Services (ICWS 2026)
  • International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2024)
• Reviewer
  • ACM Computing Surveys — 2026
  • IEEE Transactions on Services Computing — 2025
  • IEEE Transactions on Mobile Computing — 2025
  • IEEE International Conference on Big Data (IEEE BigData 2025)

Publications

• Qi Zhang, Dian Chen, Lance M. Kaplan, Audun Jøsang, Feng Chen, Dong Hyun Jeong, and Jin-Hee Cho. “X-MAP: eXplainable Misclassification Analysis and Profiling for Spam and Phishing Detection.” Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2026), Jun. 2026.
• Xinyi Zhang, Mamtaj Akter, Heajun An, Minqian Liu, Qi Zhang, Lifu Huang, Jin-Hee Cho, Pamela J. Wisniewski, and Sang Won Lee. “From Vulnerable to Resilient: Examining Parent and Teen Perceptions on How to Respond to Unwanted Cybergrooming Advances.” ACM Conference on Human Factors in Computing Systems (CHI 2026), Apr. 2026.
• Qi Zhang, Dian Chen, Lance M. Kaplan, Audun Jøsang, Feng Chen, Dong Jeong, and Jin-Hee Cho. “Beyond Binary Opinions: A Deep Reinforcement Learning-Based Approach to Uncertainty-Aware Competitive Influence Maximization.” IEEE Transactions on Network Science and Engineering, vol. 13, pp. 2219–2235, 2026.
• Heajun An, Qi Zhang, Minqian Liu, Xinyi Zhang, Sang Won Lee, Lifu Huang, Pamela J. Wisniewski, and Jin-Hee Cho. “StagePilot: A Deep Reinforcement Learning Agent for Stage-Controlled Cybergrooming Simulation.” Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL 2026).
• Dian Chen, Qi Zhang, Lance Kaplan, Audun Josang, Donghyun Jeong, Feng Chen, and Jin-Hee Cho. “fair-LDP: Uncertainty-Guided Fairness and Privacy for Federated Healthcare Learning.” IEEE International Conference on Data Mining (ICDM 2025), Dec. 2025.
• 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. “LLM Can be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Models.” Conference on Language Modeling (COLM 2025), Oct. 2025.
• Dian Chen, Qi Zhang, Lance Kaplan, Audun Josang, Donghyun Jeong, Feng Chen, and Jin-Hee Cho. “Ethical AI for Healthcare Systems: Uncertainty-Aware, Fair Federated Learning.” IEEE/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE 2025), Jun. 2025.
• Qi Zhang, Lance M. Kaplan, Audun Jøsang, Dong Hyun Jeong, Feng Chen, and Jin-Hee Cho. “Uncertainty-Aware Influence Maximization: Enhancing Propagation in Competitive Social Networks with Subjective Logic.” 2024 IEEE International Conference on Big Data (BigData 2024), pp. 2065–2071, Dec. 2024.
• Chen-Wei Chang, Shailik Sarkar, Shutonu Mitra, Qi Zhang, Hossein Salemi, Hemant Purohit, Fengxiu Zhang, Michin Hong, Jin-Hee Cho, and Chang-Tien Lu. “Exposing LLM Vulnerabilities: Adversarial Scam Detection and Performance.” IEEE BigData 2024 — Workshop on Big Data Engineering and Analytics in Cyber-Physical Systems (BigEACPS’24), Dec. 2024.
• Shutonu Mitra, Qi Zhang, Chen-Wei Chang, Hossein Salemi, Hemant Purohit, Fengxiu Zhang, Michin Hong, Chang-Tien Lu, and Jin-Hee Cho. “Towards Inclusive Cybersecurity: Protecting the Vulnerable with Social Cyber Vulnerability Metrics.” The Sixth IEEE International Conference on Trust, Privacy and Security in Intelligent Systems, and Applications (TSP) — Workshop on Inclusive AI for Online Cybersecurity, invited paper, Oct. 2024.
• Zhen Guo, Zelin Wan, Qisheng Zhang, Xujiang Zhao, Qi Zhang, Lance M. Kaplan, Audun Jøsang, Dong H. Jeong, Feng Chen, and Jin-Hee Cho. “A survey on uncertainty reasoning and quantification in belief theory and its application to deep learning.” Information Fusion, vol. 101 (2024): 101987.
• Zhen Guo, Qi Zhang, Qisheng Zhang, Lance M. Kaplan, Audun Jøsang, Feng Chen, Dong H. Jeong, and Jin-Hee Cho. “Detecting intents of fake news using uncertainty-aware deep reinforcement learning.” 2023 IEEE International Conference on Web Services (ICWS), pp. 722–724, Jul. 2023.
• Zhen Guo, Qi Zhang, Qisheng Zhang, Lance Kaplan, Audun Jøsang, Feng Chen, Donghyun Jeong, and Jin-Hee Cho. “Uncertainty-Aware Reward-based Deep Reinforcement Learning for Intent Analysis of Social Media Information.” The 1st AAAI Workshop on Uncertainty Reasoning and Quantification in Decision Making (UDM-AAAI-23), co-located with AAAI-23, Feb. 2023.

Talks

• X-MAP: eXplainable Misclassification Analysis and Profiling for Spam and Phishing Detection, ACM Capital Region Celebration of Women in Computing Conference (CAPWIC 2026), Alexandria, VA, USA, March 01, 2026
• Reinforcement Learning Approaches for Competitive Influence Maximization Under Uncertainty, Virginia Tech, Alexandria, VA, USA, November 01, 2025
• DeepSAGE: Strategic Questioning for Structured AI Counseling, Commonwealth Cyber Initiative Symposium (CCI 2025), Richmond, VA, USA, April 01, 2025
• Uncertainty-Aware Influence Maximization: Enhancing Propagation in Competitive Social Networks with Subjective Logic, IEEE International Conference on Big Data (BigData 2024), Washington, DC, USA, December 01, 2024
• Winning the Social Media Influence Battle: A New Approach to Understanding and Spreading True Information, ACM Capital Region Celebration of Women in Computing Conference (CAPWIC 2024), Charlottesville, VA, USA, April 01, 2024
• Strategic Questioning and Enhanced Engagement: Developing a Counselor Chatbot Using LLMs and Deep Reinforcement Learning for Deeper Self-Exploration and Therapeutic Dialogue, ACM Capital Region Celebration of Women in Computing Conference (CAPWIC 2025), Washington, DC, USA, March 01, 2024
• Reinforcement Learning and Its Applications, AI Awareness Workshop, Dallas College, Dallas, TX, USA, November 01, 2023
• Uncertainty-Aware Deep Reinforcement Learning-based Competitive Influence Maximization Combating False Information, Commonwealth Cyber Initiative Symposium (CCI 2023), Richmond, VA, USA, April 01, 2023