Implement Robust DPatch Attack

[deprit]

Armory Library must support custom evasion attacks designed by the user; supporting user-developed attacks requires the steps below.

• Design and implement a custom attack API that
  • Optimizes an attack over a training split and, possibly, a validation set;
  • Exposes the optimization loop to PyTorch Lightning;
  • Logs optimization metrics and attack artifiacts to MLFlow.
• Demonstrate a custom attack that
  • Implements Robust DPatch for object detection (ART implementation);
  • Optimizes the Robust DPatch attack on the VisDrone dataset
    using a pre-trained Hugging Face object detector.

[treubig26]

This has been partially addressed by PR #155, however more work remains to generalize and integrate the attack optimization as part of the armory-library API.

Specifically, a new attack optimization engine should be created that will handle instantiation of the lightning module (with more hooks/parameterization) and the trainer.

The following comments from the PR should also be addressed in a follow-on PR:

• 149 implement robust dpatch attack #155 (comment)
• 149 implement robust dpatch attack #155 (comment)
• 149 implement robust dpatch attack #155 (comment)
• 149 implement robust dpatch attack #155 (comment)
• 149 implement robust dpatch attack #155 (comment)
• 149 implement robust dpatch attack #155 (comment)