Network Security and Resilient Systems
Threat modeling, attack detection, defense mechanisms, and resilient networked computing.
Associate Professor of Computer Science
Qiang Zhi
Trustworthy, Secure, and Resilient Networked Intelligence
My research focuses on network security, trustworthy federated intelligence, privacy-preserving systems, cloud-native security, and resilient networked computing.
- Affiliation
- Jiangsu Normal University
- Office
- Office information to be added
- Keywords
- Network Security, Federated Learning Security, Cloud-Native Security
About
Research Profile
My research focuses on network security, trustworthy federated intelligence, privacy-preserving systems, and resilient networked computing.
I am particularly interested in building secure and verifiable mechanisms for distributed systems, cloud-native infrastructures, privacy-preserving search, UAV and IoV networks, and reinforcement learning for networked systems.
Research Interests
Secure Networked Systems and Trustworthy Intelligence
Trustworthy Federated Learning
Security, privacy, robustness, incentive design, and reliable collaboration across distributed clients.
Privacy-Preserving Search
Searchable encryption, verifiable computing, secure indexes, and practical privacy guarantees.
Cloud-Native and Microservice Security
Security analysis for containers, microservices, service meshes, and modern cloud-native stacks.
UAV and IoV Network Security
Secure edge intelligence, routing, collaboration, and trustworthy sensing for mobile networked systems.
Reinforcement Learning for Networks
Learning-based resource allocation, adaptive defense, and robust decision-making for networked systems.
Publications
Selected Publications
- Joint task offloading and resource allocation in multi-UAV collaborative computing via LMMARL.
- SPECTRA: Secure Framework for Adaptive Frequency Hopping and Decentralized Storage.
- DGDPFL: Dynamic Grouping and Privacy Budget Adjustment for Federated Learning in Networked Service Management.
- Collaborative Metadata Indexing: A Privacy-Preserving Framework for Metadata Management in Vehicular Networks.
- RTCD4ADS: Runtime traffic rule conflict detection for autonomous driving system.
- FedPDA: Personalized federated learning based on attribute similarity migration.
- A Dual-Layer Network Security Model for Smart Factories Based on the Sentinel Mechanism.
- An Approach to Develop Assurance Models Toward Safety of the Intended Functionality.
- ODFa2: Overall Defense Framework against Cyber-Attacks on Intelligent Connected Vehicles.
- An Efficient Multiplex Network Model for Effective Honeypot Roaming against DDoS Attacks.
- Modeling and Analyzing Honeypot Roaming with a Multi-Layer Adaptive Network Approach and Redirection Mechanism.
- Density-based clustering with differential privacy.
Students and Lab
Research Group
Our group studies secure, private, and resilient networked intelligence. We welcome motivated students interested in network security, distributed learning, and systems security.
Openings
- Prospective graduate students with systems, security, or machine learning background.
- Undergraduate research assistants interested in secure networked systems.
- Collaborators working on cloud-native, edge, UAV, or federated learning security.
Academic Service
Professional Activities
- Reviewer for journals and conferences in network security, systems, and distributed intelligence.
Contact