AI-Driven OT/ICS Cybersecurity for Power & Energy Systems
With over 15 years of experience in safety-critical infrastructure — including roads, bridges, metro rail, industrial plants, and power projects — my work has been shaped by environments where reliability, coordination, and operational discipline matter. I am a BUET graduate, and alongside my engineering career I have consistently explored computing and IT through formal study, programming, data science, and machine learning.
Today, I am focused on AI-driven Cybersecurity for Industrial Systems, integrating automation and data-driven analysis to support anomaly detection and threat modeling in power and energy environments. My long-term direction is to bridge engineering reality, cybersecurity, and intelligent automation for critical infrastructure — in ways that remain practical, explainable, and operationally safe.
My website is structured around three pillars: field experience, focused writing, and target-aligned projects.
A visual record of my work in safety-critical infrastructure—showing the environments where reliability, safety, and operational constraints matter.
Articles on AI-driven cybersecurity in gas & power—anomaly detection, process-aware defense, and practical thinking for operators and engineers.
A curated set of projects showing strength in AI, programming, automation, and security-thinking—built with clear documentation.
These photos highlight the environments and constraints that shape my approach to cybersecurity: safety, uptime, process integrity, and real-world tradeoffs.
Short, structured posts focused on OT/ICS security + AI for gas and power systems. (Start with 3 posts and grow steadily.)
What changes when uptime and safety are non-negotiable—and how defenders should adapt.
Reducing false positives by connecting signals to operations and process states.
Map cyber events to physical impact and prioritize mitigations that won’t disrupt operations.
A small set of deeply documented projects. Fewer projects, higher quality.
ML workflow practice: feature engineering, validation, tuning, and deployment mindset.
🔗 GitHub Repo | 📄 Summary PDF
Deep learning practice: architecture, training stability, evaluation discipline.
🔗 GitHub Repo | 📄 Summary PDF
Planned: OT/ICS anomaly detection (time-series telemetry + operationally meaningful alerts). Will include baselines, model comparison, false-positive control strategy, and an architecture diagram.
Live tools support your core identity (experience + blog + projects).