Implement CutMix in Numpy, PyTorch, and TensorFlow

[f4str]

Description

Implementation of the CutMix data augmentation defense in the Numpy, PyTorch, and TensorFlow frameworks.

Fixes # (issue)

Type of change

Please check all relevant options.

• Improvement (non-breaking)
• Bug fix (non-breaking)
• New feature (non-breaking)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

Testing

Please describe the tests that you ran to verify your changes. Consider listing any relevant details of your test configuration.

• Tests for the CutMix preprocessor in Numpy
• Tests for the CutMix preprocessor in PyTorch
• Tests for the CutMix preprocessor in PyTorch

Test Configuration:

• OS
• Python version
• ART version or commit number
• TensorFlow / Keras / PyTorch / MXNet version

Checklist

• My code follows the style guidelines of this project
• I have performed a self-review of my own code
• I have commented my code
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes

[codecov-commenter]

Codecov Report

Merging #1910 (580a908) into dev_1.13.0 (6e82fe1) will increase coverage by 1.31%.
The diff coverage is 73.36%.

@@              Coverage Diff               @@
##           dev_1.13.0    #1910      +/-   ##
==============================================
+ Coverage       84.25%   85.57%   +1.31%     
==============================================
  Files             254      257       +3     
  Lines           23661    23890     +229     
  Branches         4289     4340      +51     
==============================================
+ Hits            19935    20443     +508     
+ Misses           2624     2336     -288     
- Partials         1102     1111       +9     

Impacted Files	Coverage Δ
art/defences/preprocessor/cutmix/cutmix.py	72.00% <72.00%> (ø)
.../defences/preprocessor/cutmix/cutmix_tensorflow.py	72.36% <72.36%> (ø)
art/defences/preprocessor/cutmix/cutmix_pytorch.py	74.66% <74.66%> (ø)
art/defences/preprocessor/__init__.py	100.00% <100.00%> (ø)
art/attacks/evasion/boundary.py	92.72% <0.00%> (-1.22%)	⬇️
art/estimators/classification/tensorflow.py	84.30% <0.00%> (+0.20%)	⬆️
art/estimators/classification/pytorch.py	86.38% <0.00%> (+0.46%)	⬆️
art/estimators/classification/blackbox.py	98.00% <0.00%> (+2.00%)	⬆️
art/estimators/classification/lightgbm.py	95.00% <0.00%> (+6.66%)	⬆️
art/estimators/scikitlearn.py	75.00% <0.00%> (+8.33%)	⬆️
... and 10 more

[lgtm-com]

This pull request introduces 7 alerts when merging 707bfa8 into c366b1d - view on LGTM.com

new alerts:

• 3 for Redundant comparison
• 2 for Module is imported more than once
• 2 for Non-callable called

[lgtm-com]

This pull request introduces 5 alerts when merging be08f13 into dcd1fe7 - view on LGTM.com

new alerts:

• 3 for Redundant comparison
• 2 for Module is imported more than once

---

Heads-up: LGTM.com's PR analysis will be disabled on the 5th of December, and LGTM.com will be shut down ⏻ completely on the 16th of December 2022. Please enable GitHub code scanning, which uses the same CodeQL engine ⚙️ that powers LGTM.com. For more information, please check out our post on the GitHub blog.