Project case study
FGSM Adversarial Attack
Adversarial machine learning demo deployed across local and cloud environments
Fast Gradient Sign Method adversarial attacks on ML models. Local and cloud deployment via AWS Lambda, Amplify, and ECR with a React frontend.
Problem
Security risks in machine learning are often explained academically, but developers rarely get a usable demo that shows how adversarial attacks behave in practice and how to expose them safely.
Solution
This project packages FGSM attack logic into a deployable product with an API layer, frontend, and cloud infrastructure so the concept becomes tangible.
Impact
It makes adversarial ML easier to teach, test, and demonstrate while also showing deployment discipline beyond a notebook environment.
Stack and implementation notes
This project combines product thinking with technical implementation. The goal was not only to prove the underlying model or workflow, but to shape it into something understandable and usable for real people.
Technologies used here include Python, FastAPI, AWS Lambda, AWS ECR, React. The stack was chosen to keep the delivery practical while still leaving room for experimentation, iteration, and deployment.