U.S. Ph.D. from Embry-Riddle (2025), machine-learning research focus. Five first-author papers (three in IEEE Access) on trustworthy ML, proof-of-learning, and model watermarking. Twelve years architecting mission-critical systems across defence, security, and aviation.
Field notes 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.