Research

My current research spans three areas:

• Collective Intelligence and Privacy-preserving Data Sharing: Federated Learning, where organizations (e.g., hospitals) jointly train AI models while sharing only model parameters, not raw data; and, Federated Unlearning, which removes specific organizational data’s influence from a trained model to uphold the right to be forgotten.

• Network economics: Incentive mechanisms and game-theoretic analysis that reward cooperative and competitive organizations in proportion to their contributions (e.g., data volume, gains in global model performance).

• Networked systems: Blockchain for auditable, secure data sharing, and security for next-generation (5G and beyond) networks.

My past research interests include:

• Wireless Sensor Networks

• Cloud computing

• Deep Learning-based IoT systems

• Software-Defined Networking

---

Professional Activities

Invited Reviewer

• 2026: The 2026 IEEE 103rd Vehicular Technology Conference (VTC2026-Spring)

Invited Talk

• I was invited to give a talk, Data Stays, Intelligence Unites: Designing Sustainable Incentives for Privacy-Preserving AI, at the ENSURE-6G Workshop on Privacy-Preserving Machine Learning (PPML). The talk discussed why sustainable incentives, rather than algorithms alone, determine whether privacy-preserving AI systems such as Federated Learning are adopted and sustained in practice.