jaxball/advis.js

[Tensorflow.js] AdVis: Exploring real-time Adversarial Attacks in the browser with Fast Gradient Sign Method.

42
/ 100
Emerging

This interactive web tool helps researchers and students understand how small, intentional changes to an image can trick an AI image classifier. You upload an image and see how adjusting a 'perturbation strength' value dynamically alters the AI's classification scores and highlights which parts of the image are most influential. It's designed for anyone studying or curious about the vulnerabilities of machine learning models to adversarial attacks.

No commits in the last 6 months.

Use this if you want to visually and interactively explore the effects of adversarial attacks on image classification models in real-time without needing to write code.

Not ideal if you're looking for a tool to develop or implement robust adversarial training techniques or conduct large-scale attack experiments.

AI-explainability machine-learning-security computer-vision-research deep-learning-education adversarial-AI
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

50

Forks

12

Language

JavaScript

License

MIT

Last pushed

Jan 25, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jaxball/advis.js"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.