P2NIA: Privacy-Preserving Non-Iterative Auditing
(ECAI) Proposes a mutually beneficial collaboration for both the auditor and the platform: a privacy-preserving and non-iterative audit scheme that enhances fairness assessments using synthetic or local data, avoiding the challenges associated with traditional API-based audits.
- from
- Audit Algorithms
- added
- 2026-10-10
- likes
- 0
similar
-
Fairness Auditing with Multi-Agent Collaboration arxiv.org
(ECAI) Considers multiple agents working together, each auditing the same platform for different tasks.
-
Auditing link.springer.com
-
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.
-
Auditing Algorithms: On Lessons Learned and the Risks of DataMinimization dl.acm.org
(AIES) A practical audit for a well-being recommendation app developed by Telefónica (mostly on bias).
-
-
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 > 2025: “(ECAI) Proposes a mutually beneficial collaboration for both the auditor and the platform: a privacy-preserving and non-iterative audit scheme that enhances fairness assessments using synthetic or local data, avoiding the challenges associated with traditional API-based audits.”