Publications

Foundations of my LLM and RL work: deep RL, uncertainty, and cybersecurity

My research spans deep reinforcement learning, uncertainty quantification, game-theoretic decision making, and cybersecurity, and it is the foundation of the LLM post-training and evaluation work I do now. In total I have 15 papers (9 first-author), with 4 under review. A selection is below, and the full list is on Google Scholar. An asterisk (*) marks equal contribution.

Selected publications

2026

  • Cyber Deception for Mission Surveillance via Hypergame-Theoretic Deep Reinforcement Learning
    Z. Wan, J.H. Cho, M. Zhu, A. Anwar, C. Kamhoua, M. P. Singh
    IEEE Transactions on Dependable and Secure Computing (TDSC), accepted 2026

2024

  • Optimizing Effectiveness and Defense of Drone Surveillance Missions via Honey Drones
    Z. Wan, J.H. Cho, M. Zhu, A. Anwar, et al.
    ACM Transactions on Internet Technology, 2024

  • A Survey on Uncertainty Reasoning and Quantification in Belief Theory and Its Application to Deep Learning
    Z. Guo, Z. Wan, X. Zhao, Q. Zhang, Qi Zhang, A. Jøsang, L. Kaplan, et al.
    Information Fusion, 2024
    Paper

2023

  • Deception in Drone Surveillance Missions: Strategic vs. Learning Approaches
    Z. Wan, J.H. Cho, M. Zhu, A. Anwar, C. Kamhoua, M. P. Singh
    ACM MobiHoc (Mobile Computing and Networking), 2023
    Paper

  • Resisting Multiple Advanced Persistent Threats via Hypergame-Theoretic Defensive Deception
    Z. Wan, J.H. Cho, M. Zhu, A. Anwar, C. Kamhoua, M. P. Singh
    IEEE Transactions on Network and Service Management (TNSM), 2023
    Paper

2022

  • Honeypot-Based Cyber Deception Against Malicious Reconnaissance via Hypergame Theory
    A. Anwar, M. Zhu, Z. Wan, J.H. Cho, C. Kamhoua, M. P. Singh
    IEEE Global Communications Conference (GLOBECOM), 2022
    Paper

2021

  • Foureye: Defensive Deception Against Advanced Persistent Threats via Hypergame Theory
    Z. Wan, J.H. Cho, M. Zhu, A. Anwar, C. Kamhoua, et al.
    IEEE Transactions on Network and Service Management (TNSM), 2021
    Paper

  • A Survey on Centrality Metrics and Their Network Resilience Analysis
    Z. Wan, Y. Mahajan, B. Kang, T. J. Moore, J.H. Cho
    IEEE Access, 2021
    Paper

  • A Survey of Defensive Deception: Approaches Using Game Theory and Machine Learning
    M. Zhu, A. H. Anwar, Z. Wan, J.H. Cho, C. Kamhoua, M. P. Singh
    *IEEE Communications Surveys & Tutorials (CST), 2021
    Paper

  • Diversity-by-Design for Dependable and Secure Cyber-Physical Systems: A Survey
    Q. Zhang, A. Z. Mohammed, Z. Wan, J.H. Cho, T. J. Moore
    *IEEE Transactions on Network and Service Management (TNSM), 2021
    Paper

Under review

  • Decision Theory-Guided Deep Reinforcement Learning for Fast Learning
    Z. Wan, J.H. Cho, M. Zhu, A. Anwar, C. Kamhoua, M. P. Singh
    Submitted to IEEE International Conference on Robotics and Automation (ICRA)

  • DASH: Deception-Augmented Shared Mental Model for a Human-Machine Teaming System
    Z. Wan, J.H. Cho, M. Zhu, A. Anwar, C. Kamhoua, M. P. Singh
    Submitted to IEEE Transactions on Human-Machine Systems (THMS)

  • Advancing Human-Machine Teaming: Concepts, Challenges, and Applications
    D. Chen, Z. Wan, H.J. Yoon, R. He, S.W. Lee, J.H. Cho
    *Submitted to ACM Computing Surveys

  • Sustainable Smart Farm Networks: Enhancing Resilience and Efficiency with Decision Theory-Guided Deep Reinforcement Learning
    D. Chen, Z. Wan, D.S. Ha, J.H. Cho
    Submitted to ACM Transactions on Intelligent Systems and Technology (TIST)