adversarial-robustness-toolbox

adversarial-robustness-toolbox copied to clipboard

TensorFlow Addons is end of life in May 2024

3

> TensorFlow Addons (TFA) has ended development and introduction of new features. > TFA has entered a minimal maintenance and release mode until a planned end of life in May...

jamesmyatt

NaNs in Wasserstein Attack

5

**Describe the bug** The Wasserstein attack produces NaNs in the output. **To Reproduce** I believe I've produced a minimal example of the issue. You can run it on Google's Colab...

billbradley

Some question about computing the adversarial saliency map in JSMA attack

3

Hi, When using JSMA method, I found that **the implementation of adversarial saliency map of this toolbox is slightly different from the original paper:** **In this toolbox,** corresponding implementation in...

HIT1180300227

Update version of scikit-learn in setup.py and CI yml files

1

### Discussed in https://github.com/Trusted-AI/adversarial-robustness-toolbox/discussions/1950 Originally posted by **sr1998** December 3, 2022 Hi, is it possible for the library to support newer versions of scikit-learn? At the moment it supports scikit-learn=0.22.2...

beat-buesser

Regarding duplicated queries in the Square Attack

2

**Is your feature request related to a problem? Please describe.** I was benchmarking the performance of some black-box attacks and noticed that the Square Attack issued about 50% duplicated queries....

Lodour

support for yolov5-seg

1

Since yolov5 had a segmentation branch, and how to use art on the segmentation model of yolov5? Is there any plan for adding this support on yolov5-seg?

CETC-AI-TestGroup

Currently, many ART estimators and tools do not have progress bars to indicate how quickly they are training, or to display useful information such as loss and accuracy. With ART...

GiulioZizzo

Double Softmax in PyTorch image estimator for test cases.

2

Many tests use the PyTorch image estimator defined in the test utils. By default this estimator does _not_ use logits, e.g. the function signature is: `get_image_classifier_pt(from_logits=False, load_init=True, use_maxpool=True)` However, the...

GiulioZizzo

Incomplete EstimatorError when initializing attack on PyTorchRegressor

2

**Describe the bug** Initializing an attack on a PyTorchRegressor throws an EstimatorError with missing words in the message: ```EstimatorError: AutoProjectedGradientDescent requires an estimator derived from and and , the provided...

KandBM

Currently PyTorchClassifier determines the internal structure of the provided model via self._model._modules.items(). This is quite a brittle approach as it it purely dependant on how the layers were declared in...

GiulioZizzo