feat: enable privacy evaluation for models trained externally #24
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
oracle-contributor-agreement
bot
added
the
OCA Verified
YashaPushak
reviewed
Jun 23, 2025
| @@ -60,7 +60,7 @@ def __init__( | |||
| AttackRunner | |||
| """ | |||
| self.dataset = dataset | |||
| assert self.dataset.target_model_data is not None | |||
| #assert self.dataset.target_model_data is not None | |||
| assert self.dataset.attack_model_data is not None | |||
There was a problem hiding this comment.
assert statements are not recommended in python code, as there are cases in which they are ignored, depending on how you run the code, which can introduce security vulnerabilities.
The standard in this repo is to only raise exceptions from this file https://github.com/oracle/guardian-ai/blob/main/guardian_ai/utils/exception.py
There was a problem hiding this comment.
Thanks, @YashaPushak
I can take care of this one. However, I did notice that there are other assert statements in the code that were already present in the repo before my PR
@pallika @hamidmozaffari
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Outdated suggestions cannot be applied.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.
This PR introduces support for running privacy evaluation on models that were trained externally (outside the Guardian AI). This allows users to assess privacy risks, such as potential membership inference attacks, on pre-trained models without requiring them to be retrained within the framework
@pallika @YashaPushak