Open to new Opportunities in ML/AI Research • Security ML • Anomaly Detection • Time-Series • RL/Bandits
PhD (Computer Science) @ Missouri S&T • Real-time anomaly detection for CPS/ICS (smart water, smart grid, SCADA) with strict false-positive & latency constraints
I’m a computer scientist focused on securing smart-living and industrial cyber-physical systems using resilient machine learning. My research emphasizes practical detection: low false positives, measurable latency budgets, and strong empirical validation.
Real-time anomaly detection for critical infrastructure (smart water, smart grid, and ICS/SCADA). I work on distinguishing natural events from adversarial manipulation, and on context-driven feature selection under compute constraints.
Full publication list: Google Scholar.
If you need someone who can quickly absorb a new domain, formalize the problem, run clean experiments, and deliver clear writeups, this is my core workflow—especially for security, reliability, and detection problems.
Research themes I’m strongest at—optimized for impact, deployability, and explainability.
Detection pipelines that acquire only the features worth paying for—while meeting strict false-positive targets and latency caps.
Distinguishing real usage shifts (e.g., behavior changes) from subtle false-data manipulation using resilient baselines and decision logic.
Realistic testbed-style validation for grid-edge devices and smart inverters—connecting cyber events to physical consequences.
Applied research and industry-facing experience in machine learning, security, and cyber-physical systems.
Conducting advanced research in machine learning–driven security for cyber-physical systems, with emphasis on deployable anomaly detection under real-world constraints.
Industry-oriented research experience applying machine learning and data analysis techniques to security-relevant problems.
Joined after the core technical research phase to drive customer discovery and translational validation for a dementia sensing system.
Built and led technical initiatives focused on applied AI, cybersecurity education, and project-based learning.
A short curated list. For the full list, use Google Scholar.
I actively contribute to the research community through reviewing and technical evaluation.
For a quick overview of my work and roles, download the resume above.
A selection of applied research projects aligned with deployable security and detection.
Context-driven feature acquisition + detection with strict FP control under compute/latency budgets.
Distinguishing naturally occurring usage events from stealthy false-data manipulation using resilient baselines.
Testbed-style evaluation and resilience analysis for grid-edge devices under realistic operational conditions.
Studying covert channels and detection strategies for DNS-based exfiltration and secure transport patterns.
End-to-end learning that selects a small, budget-feasible subset of features (masking) before classification—balancing accuracy with sparsity and latency.
I led the translational track: customer discovery, problem validation, and go-to-market learning through NSF I-Corps (local → national), resulting in an award.
Blog posts and project notes (you can publish to /blog later). For now, this section is ready.
Conversations on technology, innovation, and leadership
Check out the full playlist on YouTube for all episodes
I’m open to ML/AI research roles, collaborations, speaking, and high-impact projects in security, anomaly detection, and CPS/ICS.
ayanfeoluwaoluyomi@gmail.com
Professional network
Open-source projects
Book a call
Ready to build something high-signal together?
Start a Conversation