Exposing the Illusion of Fairness: Auditing Vulnerabilities to Distributional Manipulation Attacks
(arXiv)
- from
- Audit Algorithms
- added
- 2026-10-10
- likes
- 0
similar
-
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.
-
Online Fairness Auditing through Iterative Refinement dl.acm.org
(KDD) Provides an adaptive process that automates the inference of probabilistic guarantees associated with estimating fairness metrics.
-
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.
-
Keeping Up with the Language Models: Robustness-Bias Interplay in NLI Data and Models arxiv.org
(Arxiv) Proposes a way to extend the shelf-life of auditing datasets by using language models themselves; also finds problems with the current bias auditing metrics and proposes alternatives -- these alternatives highlight that model brittleness superficially increased the…
Audit Algorithms › Papers > 2026: “(arXiv)”