Back to projects
ProjectUpdated Jun 18, 20265 tools

FGSM Adversarial Attack

Adversarial machine learning demo deployed across local and cloud environments

statusshipped
primaryPython
writeupnone

Overview

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

Built with a practical stack

PythonFastAPIAWS LambdaAWS ECRReact

The stack was chosen around the practical shape of the build: what needed to run in production, what needed to stay readable, and what made iteration faster.