Skip to content

Conversation

@mzweilin
Copy link
Contributor

What does this PR do?

This PR makes external attackers part of the unified Adversary object which enforces threat models.

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.

  • pytest tests

Before submitting

  • The title is self-explanatory and the description concisely explains the PR
  • My PR does only one thing, instead of bundling different changes together
  • I list all the breaking changes introduced by this pull request
  • I have commented my code
  • 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
  • I have run pre-commit hooks with pre-commit run -a command without errors

Did you have fun?

Make sure you had fun coding 🙃

@mzweilin mzweilin requested a review from dxoigmn March 23, 2023 17:21
Copy link
Contributor

@dxoigmn dxoigmn left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think this should be an Adversary and not an Attacker. But if you want to make this an attacker, then you should really get rid of PartialInstanceWrapper.



class NormalizedAdversaryAdapter(torch.nn.Module):
class NormalizedAttackerAdapter(torch.nn.Module):
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think it's fine that this is an Adversary and should probably mimic the flow of what the current Adversary class does. But instead of taking a Trainer/Attacker, it takes an attack and instead of calling fit, it just calls the attack (or directly calls run_standard_evaluation).

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants