Technical & acad projects
Exploring the Efficacy of Large Language Models (GPT-4) in Binary Reverse Engineering
Exploring the Efficacy of Large Language Models (GPT-4) in Binary Reverse Engineering
Exploring the Efficacy of Large Language Models (GPT-4) in Binary Reverse Engineering
This research assesses GPT-4's adeptness in Binary Reverse Engineering through a two-phase experiment analyzing code comprehension and malware scrutiny. Findings highlight GPT-4's general code understanding capabilities and pinpoint its varied success in intricate technical evaluations. The study emphasizes the potential and limits of Large Language Models in reverse engineering, offering valuable directions for advancing this technological domain.
More information here
Flight Delay Estimation- A Big Data ML Project
Exploring the Efficacy of Large Language Models (GPT-4) in Binary Reverse Engineering
Exploring the Efficacy of Large Language Models (GPT-4) in Binary Reverse Engineering
This project employs machine learning and PySpark to predict flight arrival delays using a comprehensive 2007 U.S. flight dataset. Focusing on enhancing airline operational efficiency and passenger experience, the project explores models like Random Forest and Linear Regression, evaluated by RMSE and R² metrics. The transition from GitHub user data to flight data analysis highlights our commitment to tackling real-world challenges in the aviation industry. GitHub Repository
Netflix Secrets - A Data Science Project
SpaceX Fellows - A Machine Learning Project
SpaceX Fellows - A Machine Learning Project
This project utilizes data science and machine learning techniques to analyze and predict Netflix viewership and IMDb ratings. The primary dataset, released by Netflix, contains around +18k movie titles with their viewing hours, enriched with additional data from the OMDB API. GitHub Repository
SpaceX Fellows - A Machine Learning Project
SpaceX Fellows - A Machine Learning Project
SpaceX Fellows - A Machine Learning Project
The SpaceX Fellows project aims to predict the successful landing of SpaceX's Falcon 9 first stage using machine learning techniques. This project utilizes data from SpaceX launches, processed and analyzed using Python, Pandas, and SQL. Key technologies employed include Jupyter notebooks for data visualization and analysis, as well as scikit-learn for building and evaluating machine learning models. The insights derived from this project can assist in strategic decision-making for competitive bidding in rocket launches. GitHub Repository
