Dr. Houbing Herbert Song
Professor · Tenured
Department of Computer Science and Electrical Engineering Department of Information Systems
About
Houbing Herbert Song is a Professor in the department of Information Systems at UMBC, where he directs the Security and Optimization for Networked Globe Laboratory (SONG Lab). He received his Ph.D. in Electrical Engineering from the University of Virginia in 2012. His research focuses on neuro-symbolic AI, anomaly detection, Artificial Intelligence of Things (AIoT), autonomous systems, and cyber-physical systems, with support from federal agencies and industry. Dr. Song is an IEEE Fellow, ACM Distinguished Member, elected Member of the European Academy of Engineering (EAE), and a Web of Science Highly Cited Researcher. He has authored more than 500 articles, edited more than 10 books, and holds two patents. He serves as Co-Editor-in-Chief of IEEE Transactions on Industrial Informatics and holds editorial and leadership roles across major IEEE and ACM communities, including the Founding Chair of the ACM Emerging Interest Group on Trustworthy and Responsible Systems (EIGTRUST). He is also an ACM Distinguished Speaker and IEEE Distinguished Lecturer/Visitor across multiple societies, including SYSC, CIS, CS, ComSoc, ITSS, and VTS, and has received numerous honors, including the IEEE Harry Rowe Mimno Award, the Research.com Rising Star of Science Award, and more than 10 Best Paper Awards.
Research interests
Neuro-symbolic AI; Trustworthy Systems; Anomaly Detection; Artificial Intelligence of Things
Teaching interests
AI/Machine Learning, Computer Networks
Education
-
Ph D, Electrical Engineering
— University of Virginia (2012) Model-Centric Approach to Discrete-Time Signal Processing for Dense Wavelength-Division Multiplexing Systems
-
MS, Civil Engineering
— University of Texas at El Paso (2006) Development and calibration of the Anisotropic Mesoscopic Simulation model for generalized vehicular traffic modeling
Publications
- GPS Spoofing on UAV Simulation using Ardupilot 2025
- A Survey on Verification and Validation, Testing and Evaluations of Neurosymbolic Artificial Intelligence 2024
- Survey: Self-Empowered Wireless Sensor Networks Security Taxonomy, Challenges and Future Research Directions
Grants and Contracts
- Collaborative Research: VINES: Track 1: NSF-JST: Neuro-symbolic AI-Native Design of Semantic Communications
- Physics-constrained machine learning-enabled efficient grain growth modeling for 3D printed metals