Education

• Ph.D. in Electrical and Computer Engineering
  University of Dayton (UD), Dayton, OH - 2022
• M.S. in Electrical and Computer Engineering
  University of Dayton (UD), Dayton, OH - 2015
• B.S. in Automation
  Dalian JiaoTong University, Dalian, Liaoning, China - 2012

Research Interests

• Network Security
• Next-Generation Networking
• Wireless Communications
• Internet-of-Things
• Artificial Intelligence

Principal Research Interests

My research focuses on secure and intelligent networking, with an emphasis on AI-driven network traffic analysis, intrusion detection, and resilient wireless, edge, and Industrial Internet of Things systems. I develop lightweight and trustworthy machine learning methods that can operate under limited computation, bandwidth, and labeled data while maintaining strong security and predictive performance. My current work explores federated learning, cross-domain adaptation, retrieval-augmented generation, and synthetic data generation for realistic cybersecurity applications. It also examines model resilience to rare-class imbalance, data poisoning, adversarial manipulation, and prompt-injection attacks. Through collaborations spanning networked systems, wireless communications, and cyber-physical applications, my broader goal is to create deployable AI solutions that improve the security, reliability, privacy, and explainability of next-generation connected infrastructure.

Awards

• U.S Department of Energy Genesis Mission Research Award, 2026
• Schrillo Faculty Research Grant Award, 2026
• Best Paper Award, IEEE Cyber Awareness and Research Symposium (CARS), 2024

Representative Publications

1. C Stolz, DP Fiadzeawu, J Zhang, S Sullivan, F Li. RCS-Fed: Rare-Class Contribution Scoring for Federated Intrusion Detection in IIoT. 2026 IEEE World AI IoT Congress (AIIoT), 0691-0696, 2026.
2. A Tiwari, S Sullivan, C Stolz, J Zhang, F Li, E Hwang. A Deployable Platform for Real-World Network Traffic Classification Edge Devices. 2026 IEEE 16th Annual Computing and Communication Workshop and Conference, 2026.
3. DP Fiadzeawu, LV Jabla, J Zhang, F Li. Beyond Accuracy: Fidelity Evaluation Framework for Synthetic Data in Network Intrusion Detection. 2026 IEEE 16th Annual Computing and Communication Workshop and Conference, 2026.
4. I Udoidiok, F Li, J Zhang. Evaluating Model Resilience to Data Poisoning Attacks: A Comparative Study. Information 17 (1), 9, 2025.
5. M Lei, J Zhang, F Li. Towards Prompt and Trustworthy SoH Monitoring for Safety-Critical Battery Systems. 2025 Cyber Awareness and Research Symposium (CARS), 1-6, 2025.
6. J Zhang, F Li. Model-Agnostic Unsupervised Detection of Prompt Injection with Multiscale Perplexity Signatures. MILCOM 2025 IEEE Military Communications Conference, 1-6, 2025.
7. DP Fiadzeawu, J Zhang, F Li. MEFA: Multisource Entropy-Weighted Feature Adaptation for Cross-Domain Intrusion Detection. Security and Privacy 8 (5), e70069, 2025.
8. M Lei, J Zhang, F Li. Unsupervised Domain Adaptation for SoC Prediction across SoH Conditions in LFP Batteries. NAECON 2025 IEEE National Aerospace and Electronics Conference, 1-5, 2025.
9. J Zhang, F Li, H Wu, V Kumar. Clustering-informed retrieval-augmented generation for llm-based log anomaly detection. NAECON 2025 IEEE National Aerospace and Electronics Conference, 1-6, 2025.
10. F Li, I Udoidiok, J Zhang. A comprehensive study on lightweight convolution techniques for malicious traffic synthesis in diffusion models. IEEE Access 13, 88306-88317, 2025.
11. I Udoidiok, B Fonkeng, J Zhang, F Li. Towards Reliable and Interference-Aware CSI Feedback with Bayesian Neural Network. International Symposium on Intelligent Computing and Networking, 481-492, 2025.

Patent

"Predicting classification labels for bioelectric signals using a neural network." U.S. Patent Application No. 18/609,211.