Guest Editor(s)
Dr. Ji Su Park
Email: jisupark@jj.ac.kr
Affiliation: Department of Computer Science Engineering, Jeonju University, Jeonju, Republic of Korea
Homepage:
Research Interests: IIoT,cloud computing, mobile computing
Prof. Yi Pan
Email: yipan@gsu.edu
Affiliation: Faculty of Computer Science and Artificial Intelligence, Shenzhen University of Advanced Technology, Shenzhen, China
Homepage:
Research Interests: bioinformatics and health Informatics, big data analytics, cloud computing, machine learning
Summary
As computation increasingly shifts from centralized clouds to the network edge, edge computing has become foundational to real-time applications in industrial IoT, connected vehicles, smart homes, and healthcare. These distributed and resource-constrained environments generate massive, continuous streams of heterogeneous data, while simultaneously facing expanded attack surfaces and limited on-device security capabilities.
This Special Issue invites original research and comprehensive review articles that leverage artificial intelligence (AI) and data analytics to address security challenges in edge computing systems. We welcome contributions that apply data-driven and AI-based methods — including deep learning, federated learning, explainable AI, and lightweight/edge AI — to analyze, detect, and defend against threats in edge and edge-cloud environments, particularly under real-time, resource-constrained, and distributed conditions.
The Special Issue aims to bring together researchers and practitioners from academia and industry to share novel methodologies, empirical findings, and practical insights that advance the state of the art in AI-driven data analytics for edge computing security.
Topics include, but are not limited to:
AI-Driven Data Analytics (Methodology)
· Real-time and streaming data analytics at the network edge
· Time-series and graph-based analysis for threat/anomaly detection
· Federated learning for privacy-preserving, distributed data analytics
· Lightweight/edge AI and model compression for on-device analytics
· Explainable AI (XAI) for interpretable security analytics
· Predictive analytics for early threat forecasting and warning
· Multimodal data fusion analysis (sensor, network traffic, log data integration)
· Data quality enhancement, automated labeling, and preprocessing for edge environments
Edge Computing Security (Application)
· AI-based intrusion and anomaly detection for IoT/edge devices
· Malware and threat detection using data-driven approaches
· Authentication and access control at the edge
· Secure and trustworthy data exchange across heterogeneous edge-cloud and multi-domain environments (e.g., Cross-Domain Solutions)
· Blockchain-assisted data integrity for edge computing security
· Adversarial machine learning: attacks and defenses in edge AI models
Governance & Policy
· AI-driven security policy automation and compliance verification
· Data governance and regulatory compliance for edge-generated data
· Risk assessment and decision-support frameworks for edge security policy-making
Keywords
edge computing, edge security, AI-driven security, data analytics, edge AI
Login
Register
Submit a Paper
Propose a Special lssue