jaxball/advis.js
[Tensorflow.js] AdVis: Exploring real-time Adversarial Attacks in the browser with Fast Gradient Sign Method.
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.
Stars
50
Forks
12
Language
JavaScript
License
MIT
Category
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.
Higher-rated alternatives
Trusted-AI/adversarial-robustness-toolbox
Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion,...
bethgelab/foolbox
A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX
cleverhans-lab/cleverhans
An adversarial example library for constructing attacks, building defenses, and benchmarking both
DSE-MSU/DeepRobust
A pytorch adversarial library for attack and defense methods on images and graphs
BorealisAI/advertorch
A Toolbox for Adversarial Robustness Research