guardian-ai

guardian-ai copied to clipboard

fixing a typo 2023 -> 2024 (this was reported by a user)

alina-yur

Feature13/recommender membership inference attack

1

This addition to GuardianAI enables the use of membership inference attacks for recommender systems. - Additional libraries: torch==2.2.1 - For testing purposes, unit tests have been included in tests/unitary/test_privacy_attacks_recommender.py -...

ihanus

### Willingness to contribute Yes. I can contribute this feature independently. ### Proposal Summary This addition to the privacy estimation tool extends its capabilities to include membership inference attacks specifically...

ihanus

Bump scikit-learn from 1.3.2 to 1.5.0

3

Bumps [scikit-learn](https://github.com/scikit-learn/scikit-learn) from 1.3.2 to 1.5.0. Release notes Sourced from scikit-learn's releases. Scikit-learn 1.5.0 We're happy to announce the 1.5.0 release. You can read the release highlights under https://scikit-learn.org/stable/auto_examples/release_highlights/plot_release_highlights_1_5_0.html and...

dependabot[bot]

This PR enables the framework to support the evaluation of models trained outside Guardian AI. These changes specifically affect the **privacy estimation** component and do not impact other parts of...

mohsinehajar

Added a guard in run_attack to handle cases where evaluate_attack returns None or an empty list. This prevents crashes when building the result string and instead returns a NO_METRICS marker.

nishanthp

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...

mohsinehajar