uncertainty-toolbox
cleverhans
Our great sponsors
| uncertainty-toolbox | cleverhans | |
|---|---|---|
| 1 | 3 | |
| 1,711 | 6,079 | |
| 3.1% | 0.0% | |
| 10.0 | 0.0 | |
| over 1 year ago | 18 days ago | |
| Python | Jupyter Notebook | |
| MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
uncertainty-toolbox
cleverhans
-
Clever Hans (Intelligence Misatributon)
I only knew of this story from looking up the name of this library on adversarial DL https://github.com/cleverhans-lab/cleverhans
- [D] DL Practitioners, Do You Use Layer Visualization Tools s.a GradCam in Your Process?
-
[D] Does anyone care about adversarial attacks anymore?
I feel as though this area has not received much attention over the last couple of years. The CleverHans project has gone stale and I haven't heard of many new results recently. Has the community lost interest in this area? Did we decide that adversarial attacks aren't such a problem in practical applications?
What are some alternatives?
TorchDrift - Drift Detection for your PyTorch Models
deepchecks - Deepchecks: Tests for Continuous Validation of ML Models & Data. Deepchecks is a holistic open-source solution for all of your AI & ML validation needs, enabling to thoroughly test your data and models from research to production.
pytea - PyTea: PyTorch Tensor shape error analyzer
advertorch - A Toolbox for Adversarial Robustness Research
AIX360 - Interpretability and explainability of data and machine learning models
backpack - BackPACK - a backpropagation package built on top of PyTorch which efficiently computes quantities other than the gradient.
aws-security-workshops - A collection of the latest AWS Security workshops
uq-vae - Solving Bayesian Inverse Problems via Variational Autoencoders
ipme - An interactive visualization tool that transforms probabilistic programming models into an "Interactive Probabilistic Models Explorer".
delve - PyTorch model training and layer saturation monitor