advboxes/AdvBox

Advbox is a toolbox to generate adversarial examples that fool neural networks in PaddlePaddle、PyTorch、Caffe2、MxNet、Keras、TensorFlow and Advbox can benchmark the robustness of machine learning models. Advbox give a command line tool to generate adversarial examples with Zero-Coding.

50
/ 100
Established

This tool helps AI engineers and security researchers evaluate the robustness of AI models. It generates 'adversarial examples'—slightly altered inputs that fool neural networks—and can also detect these deceptive inputs. You provide your AI model and data, and it outputs adversarial examples or insights into your model's vulnerabilities.

1,412 stars. No commits in the last 6 months.

Use this if you need to test how easily your AI models can be tricked by subtly manipulated data or want to build more resilient AI systems.

Not ideal if you are looking for a general machine learning library for model training or deployment, as its focus is specifically on AI security and robustness testing.

AI Security Model Robustness Adversarial AI Deepfake Detection Computer Vision Security
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

1,412

Forks

268

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Feb 15, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/advboxes/AdvBox"

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