added support for attacking an ensemble of models with loss averaging #116
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
I think it'd be better to create a separate class for this, maybe inherited from the base class. It's not common practice to optimize an attack over multiple models, so we should probably create a different class, rather than modifying the base one. @maurapintor what do you think? |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Initial support for evasion attacks Model ensembles
This pull request changes the inner loop of the evasion attack to support ensembles by passing a list of models. The attack computes gradients on the average of losses of each model.
📚 Documentation preview 📚: https://secml-torch--116.org.readthedocs.build/en/116/