Add Oracle Aligned Adversarial Training

[Zaid-Hameed]

Description

Oracle aligned adversarial training (OAAT) is an important adversarial training approach because it provides better robustness against adversarial attacks with larger perturbation magnitudes. OAAT has been proposed in paper "Scaling Adversarial Training to Large Perturbation Bounds".

Paper Link: https://link.springer.com/chapter/10.1007/978-3-031-20065-6_18

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.

• Oracle aligned adversarial training implementation produces results similar to original implementation
• All functions in implemented code work as expected

Test Configuration:

• OS: Red Hat Enterprise Linux 8.7 (Ootpa)
• Python version: 3.9.12
• ART version or commit number
• TensorFlow / Keras / PyTorch / MXNet version: PyTorch 1.13.1+cu117

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
• My changes have been tested using both CPU and GPU devices

[codecov-commenter]

Codecov Report

Merging #2348 (e472e5f) into dev_1.17.0 (ab389e7) will decrease coverage by 6.52%.
The diff coverage is 10.89%.

❗ Your organization needs to install the Codecov GitHub app to enable full functionality.

Additional details and impacted files

@@              Coverage Diff               @@
##           dev_1.17.0    #2348      +/-   ##
==============================================
- Coverage       85.60%   79.08%   -6.52%     
==============================================
  Files             324      326       +2     
  Lines           29326    29849     +523     
  Branches         5407     5514     +107     
==============================================
- Hits            25104    23606    -1498     
- Misses           2840     4920    +2080     
+ Partials         1382     1323      -59     

Files	Coverage Δ
art/defences/trainer/__init__.py	100.00% <100.00%> (ø)
art/defences/trainer/adversarial_trainer_oaat.py	62.50% <62.50%> (ø)
...fences/trainer/adversarial_trainer_oaat_pytorch.py	8.04% <8.04%> (ø)

... and 42 files with indirect coverage changes

[beat-buesser]

Hi @Zaid-Hameed Thank you very much for your pull request! I have added a few review comments, please let me know what you think?

[beat-buesser]

Hi @Zaid-Hameed Thank you very much. It looks good to me.