Bruno Fonkeng is a Computer Science Ph.D. student at UND. My work focuses on building robust, data-driven systems capable of supporting real-world cyber defense, synthetic data generation, and large-scale computational workflows. My advisor is Dr. Jielun Zhang and supported by a combination of teaching and research assistantships, contributing to UND’s initiatives in advanced computing, applied AI, and secure systems engineering.

Before pursuing my doctoral studies, I earned a Bachelor of Science (B.Sc.) in Physics from the University of Bamenda, Cameroon, where I developed strong analytical and quantitative skills foundational to my interests in scientific computing and AI. My physics training provided a rigorous mathematical background that now informs my research in computational modeling, data integrity, and algorithmic optimization.

At UND, I have completed graduate-level coursework spanning machine learning, applied machine learning, artificial intelligence, data visualization, predictive modeling, application layer security, ethical hacking, security for cloud computing, high-performance computing, computer forensics, and multiple mathematics courses including Linear Algebra and Statistical Theory, as documented in his doctoral Program of Study. I am currently advancing my training in HPC, probabilistic modeling, statistical theory, and formal methods to deepen his theoretical and applied expertise.

My research explores probabilistic generative models including GANs, VAEs, diffusion models, and other likelihood-based approaches for cybersecurity applications such as synthetic cyber-traffic generation, data augmentation, malware image synthesis, and robust anomaly detection. My long-term goal is the development of a probabilistic simulation-to-defense framework capable of generating large-scale, realistic cyber data to support defensive AI systems. My comparative investigations of multiple generative paradigms form the foundation for scalable, trustworthy model development and future publication pipelines.

What I Do Best

Machine Learning & Generative Models

I design and train machine learning models especially probabilistic models for real-world problems in cybersecurity and analytics. I care about solid evaluation, reproducible experiments, and models that actually work in practice.

Data Engineering & ML Pipelines

I build the data and infrastructure around models: ETL/ELT pipelines, real-time APIs, experiment scaffolds, and deployment workflows. From fraud detection APIs to ROI data pipelines, I focus on making ML systems reliable and production-ready.

August 2025 – Present

August 2023 – May 2025

October 2017 – August 2020