Research & Engineering
I set technical direction for secure ML and mission-critical systems — and the standards that keep them correct when things fail.
I'm Dr. Ozgur Ural — engineer, researcher, and former lead of a 14-engineer team. I've spent twelve years architecting systems that cannot be allowed to fail: ground-control software for autonomous UAVs, a national-scale data-leakage-prevention platform, and the real-time Level D flight-simulator platforms I build today at Avion. My Ph.D. in Machine Learning (ERAU, 2025) and four IEEE Access papers on proof-of-learning, model watermarking, and adversarial robustness give that engineering a research spine: I publish the methods that prove ML systems can be trusted, then apply them in production.
Leiden, Netherlands — building flight-simulation platforms, publishing ML-security research. Open to advisory, speaking, and research collaboration.
- 12+Years in mission-critical software
- Ph.D.Machine Learning · ERAU 2025
- 4IEEE Access papers · trustworthy ML
- 14Engineers led as Team Lead
Leadership & Core Domains
My work sits at the intersection of deep technical expertise and organizational scale: setting architectural direction, raising engineering standards, and ensuring that complex systems—from mission-critical C++ to cloud-native microservices—remain robust under extreme conditions.
- Engineering Leadership
Direction, standards, teams
Led a 14-engineer team that shipped a national data-leakage-prevention product; today I drive architecture decisions and technical standards that raise the bar across the engineering organization — resilience patterns, review culture, release discipline.
- Fault-Tolerant Distributed Systems
Fault-tolerant by design
Real-time simulation platforms and cloud-native services (C++, Scala, TypeScript, gRPC) built on distributed protocols whose outputs and state can be audited end-to-end without compromising latency.
- Trustworthy ML & Security
Securing AI pipelines
Deep domain expertise in defending ML training integrity against spoofing attacks. My Ph.D. and IEEE-published research focus on feature-based model watermarking and proof-of-learning verification.
- Adversarial Robustness
Models that survive adversaries
Bridging research and production by ensuring models survive contact with adversaries. Evaluating provenance verification, adversarial examples, and the limits of claimed model identities.
Timeline
- Dec 2025 Published SecurePoL: Integration of Watermarking with Proof-of-Learning to Enhance Security Against Spoofing Attacks in IEEE Access. Read paper.
- Dec 2025 Joined the Program Committee for the 2nd Workshop on NLP Applied to Information and Cyber Security (NLPAICS 2026), University of Alicante. Conference.
- 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.
- 2021–2025 Graduate Research Assistant at Embry-Riddle Aeronautical University. Four IEEE Access publications on proof-of-learning and model watermarking.
- Nov 2024 First-author paper Feature-Based Model Watermarking for PoL in IEEE Access. Read paper.
- Dec 2023 Published the survey Blockchain-Enhanced Machine Learning in IEEE Access. Read paper.
- Oct 2023 Joined Avion Full Flight Simulators as Senior Software Engineer. Architecting real-time simulation platforms and cloud-native infrastructure for Level D flight simulators.
- May 2021 Published Automatic Detection of Cyber Security Events from Turkish Twitter Stream and Newspaper Data at ICISSP. Read paper.
- 2020–2021 Software Team Lead at Havelsan. Led a 14-engineer team delivering the Havelsan DLP data leakage prevention product for defence and government clients.
- 2019–2020 Expert Software Engineer at STM Defence Technologies. Contributed to the architecture of the mission-control and ground-control systems for the Kargu autonomous tactical UAV and Togan reconnaissance UAV.
- 2014–2019 Expert Software Engineer at Comodo Cybersecurity. Led design and architecture of the Secure Web Gateway, enterprise Patch Manager, and the Chromium-based Dragon browser.
Selected Work
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, or speaking engagements, reach out by email, or browse my publications, projects, and technical writing.