MSc Computer Science — Adaptive Cybersecurity
University of Galway, Ireland
2025 – 2026
MSc Adaptive Cybersecurity, University of Galway. I build and break detection systems — from LLM prompt-injection classifiers to network intrusion detection — and I like problems where the model has to survive contact with an adversary.
I'm finishing an MSc in Adaptive Cybersecurity at the University of Galway, with a B.Eng. in Computer Engineering from the University of Mumbai before that. Most of my project work sits at the intersection of security and machine learning: training classifiers, stress-testing them against adversarial input, and figuring out why they fail before someone else finds out for me. I'm comfortable across the stack — from PyTorch model training to REST APIs to Linux and packet-level tools like Wireshark and Suricata.
A model-agnostic proxy layer that intercepts and classifies prompts before they reach an LLM, deciding Allow or Block. Benchmarked three model families on 20,662 prompts; the best performer was a fine-tuned ModernBERT classifier. Along the way, I found systematic label noise in a public benchmark dataset, and separately found that a detector trained only on direct injection attacks failed badly on indirect ones — both problems I fixed and measured.
A PyTorch model trained to classify network attack types across two CIC-IDS datasets, reaching over 98% accuracy. The more interesting part was studying domain drift — how well a model trained on one year's traffic patterns holds up against the next year's.
My B.Eng. final-year project: a full-stack, decentralised messaging platform using cryptographic hashing to guarantee message integrity, with no single point of failure. Protocol design, smart contract logic, and a lightweight web interface, end to end.
A classifier trained on linguistic and structural features of phishing emails, reaching 92% accuracy, with an automated test pipeline to measure performance across datasets.
A cross-platform app with end-to-end encrypted storage and two-factor authentication, built with JavaScript on the frontend and SQL for persistence, talking to a REST API.
Python, Java, JavaScript, C, SQL
PyTorch, Scikit-learn, Pandas, NumPy, Tableau
REST APIs, JSON, HTML, CSS
MySQL, PostgreSQL (basic), MySQL Workbench
Wireshark, Suricata, Snort, Splunk (basics), John the Ripper, TCP/IP fundamentals, Network Security, Cryptography, Threat Analysis
Git, VS Code, Linux