A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.
U.S. Ph.D. from Embry-Riddle (2025), machine-learning research focus. Three IEEE Access papers on trustworthy ML, proof-of-learning, and model watermarking. Twelve years architecting mission-critical systems across defence, security, and aviation.
Technical writing on machine-learning security, proof-of-learning, distributed systems, and the engineering of high-reliability software, written for ML researchers, senior engineers, and technical leaders.
Posts organised by category: machine learning, security, engineering, and more.
Browse all publications, talks, and portfolio items on ozgurural.github.io.
Slow, indirect writing about machine learning, security, and the systems we are quietly building.
What a ledger actually buys machine learning: consensus that trains instead of hashing (PoL, PoDL, PoQ), incentive contracts that pay for the improvement you caused, and the measured limits DeepChain and LearningChain ran into.
Building a cyber-security event detector with no labelled corpus: learning the keyword vector from the nic.tr attack, A/B testing it on false positives, normalising Turkish morphology, and detecting events as an anomaly in entity mentions.
What hard real time actually costs in a Level D full-flight simulator: the 150 ms transport-delay gate, why the mean frame time is the wrong statistic, and how latency and reliability compose across a rack of hosts.
A cinematic, PhD-level explainer on gradient descent, momentum, and why high-dimensional loss landscapes are ruled by saddle points, not local minima.
A cinematic explainer on how smart contracts and prediction markets can act as incentive-compatible coordination with no trusted central party.
A cinematic, PhD-level explainer on the convergence of machine learning and decentralized oracle networks.
Final weights are a snapshot anyone can copy, but the path that produced them is a one-way function of compute. A cinematic, PhD-level explainer of Proof-of-Learning.
Why ‘6 confirmations’ is a probability, not a promise. A cinematic, PhD-level walk through the double-spend math of Bitcoin’s whitepaper §11.
Majority voting buys superlinear safety, until correlation installs a floor you can’t vote past. A cinematic, PhD-level explainer ending in the Ariane 5 disaster.
A cinematic explainer comparing ML watermarking strategies: parameter perturbations, feature triggers, generative green-lists, and auxiliary heads.
How a watermark too faint to see in any single weight becomes a courtroom-grade signature across thousands of them. A cinematic, PhD-level Z-test explainer.
Block Race · Model Heist Detector · Proof-of-Learning (SecurePoL) · Redundancy Reactor · Gradient Pinball · ML Oracles · Watermarking Models · Blockchain-Enhanced ML. Real research math, animated from the equation up.
Essays and notes on system architecture, engineering leadership, the academia-to-industry transition, and what twelve years of shipping mission-critical software teaches about building resilient systems.
Research code, interactive demos, and production systems by Dr. Ozgur Ural: SecurePoL proof-of-learning security, model watermarking, UAV ground control, Level D flight-simulation platforms, and clinical tooling.
Peer-reviewed publications by Dr. Ozgur Ural on proof-of-learning, model watermarking, adversarial robustness, and blockchain-enhanced machine learning.
Technical advisory, ML-security and model-provenance review, conference speaking, plus peer review and program-committee service across machine-learning security and distributed systems.
A full list of all posts, pages, and publications on ozgurural.github.io.
Privacy policy and terms of use for ozgurural.github.io.
Exploring the rapid advancements in generative audio and how sequence modeling has solved long-range dependencies in AI music generation.
What if flight simulators are the AI proving ground nobody is talking about? Three years inside Avion.
Entrepreneurs, researchers, and engineers live in a torrent of guidance. Podcasts, newsletters, and mentors offer conflicting prescriptions, each delivered w…
Scaling conversations dominate startup culture, yet the first question any product must answer is painfully small: will even one person use it when given the…
Working on simulator software, defensive cybersecurity platforms, and doctoral research has taught me that durable progress rarely starts with a perfect road…
Every engineer knows the temptation of the “five-minute hack.” A bug appears, the schedule is tight, and a clever shortcut promises to save the day. Weeks la…
Before a developer ever sees your landing page, they might encounter your README. For many technical products, documentation is the first user interface. It …
Why early-stage engineering teams should hire for breadth and learning rate, and how generalists become the connective tissue that later scales into specialists.
Engineering teams love new tools. The promise of faster development, cleaner abstractions, or a more elegant stack is hard to resist. Yet every adoption deci…
Reflections on METU Sailing Club: racing on the Aegean coast in Urla, Bodrum, and Marmaris, and what competitive sailing taught me about teamwork.
Product launches often steal the spotlight, but the feedback gathered during early beta testing quietly determines whether launch day is a victory lap or a s…
It started while I was nursing a Saturday-morning coffee and catching up on YouTube. Around the 11:20 mark of this talk, the speaker described the choreograp…
Proof of Learning (PoL) verifies that a model was genuinely trained on claimed data by providing verifiable evidence of the training process. I first felt th…
Embarking on a PhD in Florida means waking up to salt air, sunscreen reminders, and the low rumble of aircraft testing engines at Embry-Riddle Aeronautical U…
Model watermarking embeds identifiable patterns into a model’s parameters or outputs so that ownership can be demonstrated without access to the original tra…
Machine learning (ML) is increasingly used to make blockchain networks more secure, efficient, and user-friendly. When I co-authored our survey on blockchain…
Traditional agile boards depend on centralized tools and manual updates. As projects span multiple organizations and trust boundaries, these boards struggle …
How blockchain’s immutable ledgers and decentralized governance address auditability, provenance, and incentive-alignment challenges in machine-learning pipelines.
Consider this your two-minute hangar brief. Between February 2019 and November 2020, I served as an Expert Software Engineer at STM Defence Technologies in A…
Living as an expat has given me the chance to compare daily life in the United States and the Netherlands in a way that guidebooks never could. My notebook i…
Code for paper ‘Adversary examples’ for Proof of Learning
Official code & experiments for my PhD dissertation: ‘Enhancing Security of Proof-of-Learning Against Spoofing Attacks Using Advanced Model Watermarking.’
Python’s versatility allows it to create tools for a broad spectrum of professional fields. In this post I walk through building an image measurement to…
The conference talk behind the ICISSP 2021 paper: what an agglutinative language does to keyword detection, and why the false-positive rate is the number that decides whether a rare-event detector is usable.
My Master of Science Thesis Project related researches, projects and documents.
Video demonstration of the Secure Proxy on Cloud paper, covering architecture motivation, implementation details, and development roadmap.
Published in Turkish Autonomous Robots Conference, 2014
Undergraduate capstone project demonstrating an autonomous cargo and mail delivery robot, presented at the Turkish Autonomous Robots Conference.
Recommended citation: Ural, O. (2014). Autonomous Cargo and Mail Delivery. Turkish Autonomous Robots Conference, Ankara, Turkey.
Read paper
Published in Technical Report (ResearchGate), 2016
Technical report on a secure proxy architecture for cloud-based services.
Recommended citation: Ural, O. (2016). "Secure Proxy on Cloud." Technical report. DOI: 10.13140/RG.2.2.24058.08649.
Read paper
Published in Master's Thesis, 2019
Master’s thesis introducing NLP methods for detecting cyber-security events in Turkish social media and news streams, advised by Prof. Cengiz Acartürk and the basis of the later ICISSP 2021 paper.
Recommended citation: Ural, O. (2019). Automatic Detection of Cyber Security Events from Turkish Twitter Stream and Turkish Newspaper Data. Master's Thesis, Middle East Technical University, Ankara, Turkey.
Read paper
Published in Proceedings of the 7th International Conference on Information Systems Security and Privacy (ICISSP), 2021
NLP-based pipeline for automated detection of cybersecurity incidents from Turkish Twitter and news streams using TF-IDF and ensemble classifiers.
Recommended citation: Ural, O. and Acartürk, C. (2021). "Automatic Detection of Cyber Security Events from Turkish Twitter Stream and Newspaper Data." In Proceedings of the 7th International Conference on Information Systems Security and Privacy (ICISSP), pp. 66-76. DOI: 10.5220/0010201600660076.
Read paper
Published in IEEE Access, 2023
Comprehensive survey of blockchain-enhanced machine learning: consensus-driven data provenance, federated learning on-chain, and incentive mechanisms across 120+ papers.
Recommended citation: Ural, O. and Yoshigoe, K. (2023). Survey on Blockchain-Enhanced Machine Learning. IEEE Access, pp. 145331-145362. DOI: 10.1109/ACCESS.2023.3344669.
Read paper
Published in IEEE Access, 2024
Feature-based model watermarking scheme that binds ownership proofs to internal activations, surviving fine-tuning and transfer attacks on Proof-of-Learning.
Recommended citation: Ural, O. and Yoshigoe, K. (2024). Enhancing Security of Proof-of-Learning against Spoofing Attacks using Feature-Based Model Watermarking. IEEE Access. DOI: 10.1109/ACCESS.2024.3489776.
Read paper
Published in Doctoral Dissertation, 2025
Doctoral research developing SecurePoL, a dual-layer framework coupling Proof-of-Learning trajectory logs with three orthogonal watermarking strategies.
Recommended citation: Ural, O. (2025). Enhancing Proof-of-Learning Security Against Spoofing Attacks Using Model Watermarking. Doctoral dissertation, Embry-Riddle Aeronautical University.
Read paper
Published in IEEE Access, 2025
Dual-layer framework coupling immutable Proof-of-Learning logs with three watermarking strategies, so verification succeeds only when both the training trajectory and the watermark are consistent.
Recommended citation: Ural, O. and Yoshigoe, K. (2025). SecurePoL: Integration of Watermarking With Proof-of-Learning to Enhance Security Against Spoofing Attacks. IEEE Access, vol. 13, pp. 213067-213091. DOI: 10.1109/ACCESS.2025.3642198.
Read paper