Dr. Ozgur Ural
Building secure, distributed machine learning for systems that cannot fail.
I'm Dr. Ozgur Ural — a senior engineer and researcher operating at the intersection of artificial intelligence, distributed systems, and cybersecurity. My work spans peer-reviewed research on proof-of-learning and model watermarking, real-time C++ kernels powering FAA Level-D flight simulators, and cloud-native services in production. I help teams move trustworthy AI from paper to runtime.
- 11+Years engineering
- Ph.D.ERAU · 2025
- 4IEEE Access papers
- PCNLPAICS 2026
Focus areas
- AI / ML Security
Trustworthy machine learning
Proof-of-Learning protocols, feature-based model watermarking, adversarial robustness, blockchain-enhanced ML — published in IEEE Access.
- Distributed Systems
Production-grade architecture
Cloud-native services in Scala, TypeScript, gRPC. Designing for scale, resilience, and verifiability across heterogeneous workloads.
- High-Reliability
Aerospace simulation
Real-time C++ kernels behind FAA Level-D Full Flight Simulators at Avion FFS — software where downtime is unacceptable.
- Leadership & Service
Cross-functional direction
A decade leading engineers, mentoring researchers, and chairing technical strategy. NLPAICS 2026 PC; reviewer for IEEE Access & TÜBİTAK.
Currently
Real-time simulation & flight-grade engineering
Architecting C++ simulation kernels and supporting cloud services for certified flight training devices in Leiden, Netherlands.
Proof-of-Learning & Model Watermarking
Continuing research on integrity verification of ML training — extending the SecurePoL framework introduced in my dissertation.
NLP for Information & Cyber Security
Reviewing for the 2nd Workshop on NLP Applied to Information and Cyber Security at the University of Alicante.
Recent
- Dec 2025 Joined the Program Committee for the 2nd Workshop on NLP Applied to Information and Cyber Security (NLPAICS 2026), University of Alicante. Conference website.
- Dec 2025 Published SecurePoL: Integration of Watermarking with Proof-of-Learning to Enhance Security Against Spoofing Attacks in IEEE Access. Read paper.
- Aug 2025 Conferred Ph.D. in Electrical Engineering & Computer Science (ERAU). Dissertation: Enhancing Proof-of-Learning Security Against Spoofing Attacks Using Model Watermarking. Advisor: Dr. Kenji Yoshigoe. Dissertation · Verify diploma.
- Jul 2025 Successfully defended Ph.D. dissertation.
- Nov 2024 Published Enhancing Security of Proof-of-Learning against Spoofing Attacks Using Feature-Based Model Watermarking in IEEE Access. Read paper.
- Dec 2023 Published the survey Survey on Blockchain-Enhanced Machine Learning in IEEE Access. Read paper.
- May 2021 Published Automatic Detection of Cyber Security Events from Turkish Twitter Stream and Newspaper Data at ICISSP. Read paper.
Selected publications
SecurePoL: Watermarking + Proof-of-Learning
Defends proof-of-learning protocols against spoofing by integrating feature-based model watermarking with verification.
Enhancing Proof-of-Learning Security Against Spoofing Attacks
Doctoral thesis formalizing watermark-augmented PoL, threat models, and empirical robustness analysis.
Feature-Based Model Watermarking for PoL
First-author paper introducing the watermarking-based defense layer for proof-of-learning systems.
Survey on Blockchain-Enhanced Machine Learning
Comprehensive survey of the design space at the intersection of distributed ledgers and learning systems.
Get in touch
For research collaboration, technical advisory, speaking, or hiring conversations, reach me by email, or browse my publications, open-source projects, professional service, and technical writing.