Definition
Nada Golmie is an American computer scientist and academic researcher whose work focuses on cybersecurity, cryptography, and the security of machine learning systems.
Overview
Golmie holds a faculty position in the Department of Computer Science at the University of Virginia, where she conducts research on a variety of topics including side‑channel attacks, privacy‑preserving data analysis, and adversarial machine learning. She has authored and co‑authored numerous peer‑reviewed papers in leading conferences and journals such as IEEE Security & Privacy, USENIX Security, and the ACM Conference on Computer and Communications Security (CCS). In addition to her research activities, Golmie teaches undergraduate and graduate courses related to computer security and serves on program committees for major security venues.
Etymology/Origin
The given name “Nada” is of Arabic origin, meaning “dew” or “generosity.” The surname “Golmie” is less common and appears to be of Eastern European (possibly Polish or Czech) linguistic heritage, though precise etymological details are not publicly documented.
Characteristics
-
Research Areas:
- Cryptographic protocol design and analysis.
- Side‑channel and fault‑injection attacks on hardware and software systems.
- Security and privacy of machine‑learning models, including adversarial robustness and differential privacy.
- Secure data sharing and privacy‑preserving analytics.
-
Publications and Contributions:
- Papers on novel side‑channel attack methodologies that exploit electromagnetic emanations from embedded devices.
- Studies demonstrating vulnerabilities in deep‑learning classifiers to crafted adversarial inputs.
- Development of frameworks for evaluating privacy risks in federated learning environments.
-
Professional Service:
- Membership on the steering committees of several cybersecurity conferences.
- Reviewer for journals such as IEEE Transactions on Information Forensics and Security and Journal of Cryptology.
-
Recognition:
- Recipient of research awards from the National Science Foundation (NSF) for proposals related to secure machine learning.
- Listed as an invited speaker at academic workshops on privacy and security.
Related Topics
- Cybersecurity
- Cryptography
- Adversarial Machine Learning
- Side‑Channel Attacks
- Differential Privacy
- Federated Learning
Note: While the above information is drawn from publicly available academic and institutional sources, specific biographical details such as exact educational background and award dates are not fully verified.