Distill-and-Compare: Auditing Black-Box Models Using Transparent Model Distillation
(AIES) Treats black box models as teachers, training transparent student models to mimic the risk scores assigned by black-box models.
- from
- Audit Algorithms
- added
- 2026-10-10
- likes
- 0
similar
-
Auditing Black-Box Models for Indirect Influence arxiv.org
(ICDM) Evaluate the influence of a variable on a black-box model by "cleverly" removing it from the dataset and looking at the accuracy gap
-
Auditing fairness under unawareness through counterfactual reasoning sciencedirect.com
(Information Processing & Management) Shows how to unveil whether a black-box model, complying with the regulations, is still biased or not.
-
FairLens: Auditing black-box clinical decision support systems sciencedirect.com
(Information Processing & Management) Presents a pipeline to detect and explain potential fairness issues in Clinical DSS, by comparing different multi-label classification disparity measures.
-
Under manipulations, are some AI models harder to audit? grodino.github.io
(SATML) Relates the difficulty of black-box audits to the capacity of the targeted models, using the Rademacher complexity.
-
Auditing Fairness by Betting arxiv.org
(Neurips) [Code] Sequential methods that allows for the continuous monitoring of incoming data from a black-box classifier or regressor.
-
Active Fairness Auditing proceedings.mlr.press
(ICML) Studies of query-based auditing algorithms that can estimate the demographic parity of ML models in a query-efficient manner.
Audit Algorithms › Papers > 2018: “(AIES) Treats black box models as teachers, training transparent student models to mimic the risk scores assigned by black-box models.”