Skip to content
View hinnazeejah's full-sized avatar

Block or report hinnazeejah

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
hinnazeejah/README.md

Hi, I'm Hinna!

I'm a recent graduate of St. John's University with a degree in Cybersecurity Systems!

I love working on problems through data analysis and predictive modeling. I’m big on continuously learning and building my skills, and believe taking initiative is key to growth. I recently wrapped up an internship at Rivian as a Cybersecurity Analyst, where I worked on third-party risk assessments and supplier monitoring. I am now an intern for the FBI! Outside of work, I’m actively building machine learning models and deepening my understanding of cybersecurity tools and threat intelligence platforms.

I’m currently looking for a full-time opportunity where I can contribute to innovative projects and continue learning from industry professionals — got any leads? Let’s connect!


Featured Project 1: Foundation Models for Satellite Image Intelligence

What I Did:
Collaborated on a machine learning research project focused on classifying icebergs vs. vessels in Synthetic Aperture Radar (SAR) imagery. Contributed to feature extraction and embedding workflows, compared baseline ML models with pretrained foundation-model embeddings (ViT and ConvNeXt), and supported evaluation and benchmarking to identify the most effective approach for maritime object detection.

Tools: Python, scikit-learn, PyTorch, TensorFlow/Keras, HuggingFace Transformers, NumPy, Pandas, Matplotlib, Jupyter
Result: Achieved 96% classification accuracy and 98.5% ROC-AUC using a baseline MLP model. Demonstrated that while pretrained embeddings improved feature representation, a strong baseline model best met business and performance requirements for this task.

Curious? Check out the full project here

Featured Project 2: ML-Based Web Attack Classification for TANNER

What I Did:
Built a machine learning-powered system that replaced traditional regex-based detection methods, significantly improving both accuracy and efficiency. I engineered a comprehensive dataset, performed extensive preprocessing, and trained multi-label classification models—achieving a 94% accuracy rate using a Random Forest classifier.

Tools: Python, scikit-learn, Pandas, NumPy, TF-IDF, Random Forest
Result: Replaced manual rule-based detection with an automated, intelligent classification system ready for production use.

Curious? Check out the full project here

Featured Project 3: Pneumonia Detection System

What I Did
Developed a medical imaging AI system using EfficientNet to analyze chest X-ray images for pneumonia detection with 94%+ accuracy. I trained the model on open datasets, optimized it for Apple Silicon (MPS), and built a CustomTkinter GUI for user-friendly, real-time diagnosis.

Tools: Python, PyTorch, PIL, CustomTkinter
Result: Delivered sub-second inference speed and a pink-themed diagnostic interface designed for research, education, and preliminary screening.

Curious? Check out the full project here


Tech Stack

  • Languages: Python, Java
  • Data Science & ML: Pandas, NumPy, scikit-learn, TensorFlow
  • Web Development: HTML, CSS, JavaScript (basic), Node.js
  • Tools: Jupyter Notebooks, Google Colab, Git, GitHub
  • Databases: SQL, MySQL

Projects

STJ ACM Website – Website for ACM Members at St. John's University

🔗 [View Project README] What I Did:
Designed and developed a sleek, responsive site for the ACM chapter to share updates, events, and technical blog posts. I integrated a Contentful CMS backend so non-technical members could easily manage blog content without editing code.
Tech Stack: Next.js 15, TypeScript, Tailwind CSS, Framer Motion, React 18+, Contentful CMS, Vercel
Learnings:
Learned how to connect a headless CMS to a modern React stack and improved my frontend development and deployment skills.


CompTIA Prep Discord Bot – A Discord bot that helps users prepare for CompTIA exams

🔗 [View Project README]
What I Did:
Built a command-based bot that quizzes users on CompTIA Security+, Network+, and A+ exam topics, providing explanations and tracking progress.
Tech Stack: Python, Discord API
Learnings:
Strengthened my understanding of CompTIA topics, API integrations, and user interaction flows within Discord environments.


PrepPals – AI-Powered Interview Prep Discord Bot

🔗 [View Project README] What I Did:
Collaborated with a team of four to build an intelligent Discord bot that helps students prepare for interviews through real-time, personalized guidance. The bot uses open-source LLMs and web scraping to extract key information from resumes and webpages, then delivers customized prep plans and advice.

Tech Stack: Python, HuggingFace Embeddings, Retrieval-Augmented Generation (RAG), OpenAI GPT-4, Discord API
Learnings:
Gained hands-on experience working with large language models, embedding generation, and real-time bot interactions. Also improved my collaboration skills in a fast-paced, team-based project setting.

How to Reach Me


Fun Fact

I’ve visited over 15 countries and love finding inspiration in different cultures, conversations, and experiences 🌍✈️

Popular repositories Loading

  1. tanner tanner Public

    Forked from mushorg/tanner

    He who flays the hide

    Jupyter Notebook 2

  2. CompTIAPrepBot CompTIAPrepBot Public

    The CompTIA Prep Discord Bot is designed to assist students and aspiring IT and cybersecurity professionals in preparing for the CompTIA certification exams.

    Python 1

  3. PrepPals PrepPals Public

    PrepPals is a Discord bot designed to assist students in interview preparation by utilizing open-source large language models. Developed by a team of four, it extracts key information from students…

    Python

  4. hinnazeejah hinnazeejah Public

    Config files for my GitHub profile.

  5. CardsForMentalHealthWebsite CardsForMentalHealthWebsite Public

    TypeScript

  6. web-client web-client Public

    Forked from KomMonitor/web-client

    JavaScript