Name: adversarial-robustness-toolbox
Owner: International Business Machines
Description: This is a library dedicated to adversarial machine learning. Its purpose is to allow rapid crafting and analysis of attacks and defense methods for machine learning models. The Adversarial Robustness Toolbox provides an implementation for many state-of-the-art methods for attacking and defending classifiers. https://developer.ibm.com/code/open/projects/adversarial-robustness-toolbox/
Created: 2018-03-15 14:40:43.0
Updated: 2018-05-24 13:15:33.0
Pushed: 2018-05-10 14:37:01.0
Size: 2916
Language: Python
GitHub Committers
User | Most Recent Commit | # Commits |
---|
Other Committers
User | Most Recent Commit | # Commits |
---|
This is a library dedicated to adversarial machine learning. Its purpose is to allow rapid crafting and analysis of attacks and defense methods for machine learning models. The Adversarial Robustness Toolbox provides an implementation for many state-of-the-art methods for attacking and defending classifiers.
The library is still under development. Feedback, bug reports and extension requests are highly appreciated.
The Adversarial Robustness Toolbox contains implementations of the following attacks:
The following defense methods are also supported:
The Adversarial Robustness Toolbox is designed to run with Python 3 (and most likely Python 2 with small changes). You can either download the source code or clone the repository in your directory of choice:
clone https://github.com/IBM/adversarial-robustness-toolbox
To install the project dependencies, use the requirements file:
install .
The library comes with a basic set of unit tests. To check your install, you can run all the unit tests by calling in the library folder:
run_tests.sh
The configuration file config/config.ini
allows to set custom paths for data. By default, data is downloaded in the data
folder as follows:
AULT]
ile=LOCAL
AL]
_path=./data
t_path=./data/mnist
r10_path=./data/cifar-10
0_path=./data/stl-10
If the datasets are not present at the indicated path, loading them will also download the data.
Some examples of how to use Nemesis when writing your own code can be found in the examples
folder. See examples/README.md
for more information about what each example does. To run an example, use the following command:
on3 examples/<example_name>.py