microsoft/denoised-smoothing

Provably defending pretrained classifiers including the Azure, Google, AWS, and Clarifai APIs

43
/ 100
Emerging

This project helps machine learning engineers and researchers make their image classification models more reliable against subtle, malicious alterations to images. It takes an existing image classifier, including those from cloud providers like Azure, Google, AWS, or Clarifai, and applies 'denoised smoothing' to produce a more robust classifier. The output is a model that can confidently classify images even when they've been tampered with in ways that are hard for humans to detect.

102 stars. No commits in the last 6 months.

Use this if you need to ensure the trustworthiness and integrity of your image classification systems, especially in security-sensitive applications where adversaries might try to trick your models.

Not ideal if your primary concern is raw classification accuracy on clean data, or if you are working with data types other than images.

image-classification machine-learning-security adversarial-robustness computer-vision AI-safety
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

102

Forks

19

Language

Jupyter Notebook

License

MIT

Last pushed

Apr 02, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/microsoft/denoised-smoothing"

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