Matches in SemOpenAlex for { <https://semopenalex.org/work/W4320858396> ?p ?o ?g. }
Showing items 1 to 66 of
66
with 100 items per page.
- W4320858396 abstract "Existing regulations prohibit model developers from accessing protected attributes (gender, race, etc.), often resulting in fairness assessments on populations without knowing their protected groups. In such scenarios, institutions often adopt a separation between the model developers (who train models with no access to the protected attributes) and a compliance team (who may have access to the entire dataset for auditing purpose). However, the model developers might be allowed to test their models for bias by querying the compliance team for group fairness metrics. In this paper, we first demonstrate that simply querying for fairness metrics, such as statistical parity and equalized odds can leak the protected attributes of individuals to the model developers. We demonstrate that there always exist strategies by which the model developers can identify the protected attribute of a targeted individual in the test dataset from just a single query. In particular, we show that one can reconstruct the protected attributes of all the individuals from O(Nk log n/Nk) queries when Nk<<n using techniques from compressed sensing (n: size of the test dataset, Nk: size of smallest group). Our results pose an interesting debate in algorithmic fairness: should querying for fairness metrics be viewed as a neutral-valued solution to ensure compliance with regulations? Or, does it constitute a violation of regulations and privacy if the number of queries answered is enough for the model developers to identify the protected attributes of specific individuals? To address this supposed violation, we also propose Attribute-Conceal, a novel technique that achieves differential privacy by calibrating noise to the smooth sensitivity of our bias query, outperforming naive techniques such as Laplace mechanism. We also include experimental results on the Adult dataset and synthetic data (broad range of parameters)." @default.
- W4320858396 created "2023-02-16" @default.
- W4320858396 creator A5035222388 @default.
- W4320858396 creator A5072071140 @default.
- W4320858396 creator A5076671605 @default.
- W4320858396 date "2022-11-03" @default.
- W4320858396 modified "2023-09-28" @default.
- W4320858396 title "Can Querying for Bias Leak Protected Attributes? Achieving Privacy With Smooth Sensitivity" @default.
- W4320858396 doi "https://doi.org/10.48550/arxiv.2211.02139" @default.
- W4320858396 hasPublicationYear "2022" @default.
- W4320858396 type Work @default.
- W4320858396 citedByCount "0" @default.
- W4320858396 crossrefType "posted-content" @default.
- W4320858396 hasAuthorship W4320858396A5035222388 @default.
- W4320858396 hasAuthorship W4320858396A5072071140 @default.
- W4320858396 hasAuthorship W4320858396A5076671605 @default.
- W4320858396 hasConcept C119857082 @default.
- W4320858396 hasConcept C121955636 @default.
- W4320858396 hasConcept C124101348 @default.
- W4320858396 hasConcept C137822555 @default.
- W4320858396 hasConcept C143095724 @default.
- W4320858396 hasConcept C144133560 @default.
- W4320858396 hasConcept C151730666 @default.
- W4320858396 hasConcept C151956035 @default.
- W4320858396 hasConcept C15744967 @default.
- W4320858396 hasConcept C199521495 @default.
- W4320858396 hasConcept C2777267654 @default.
- W4320858396 hasConcept C2781460075 @default.
- W4320858396 hasConcept C38652104 @default.
- W4320858396 hasConcept C41008148 @default.
- W4320858396 hasConcept C77088390 @default.
- W4320858396 hasConcept C77805123 @default.
- W4320858396 hasConcept C86803240 @default.
- W4320858396 hasConceptScore W4320858396C119857082 @default.
- W4320858396 hasConceptScore W4320858396C121955636 @default.
- W4320858396 hasConceptScore W4320858396C124101348 @default.
- W4320858396 hasConceptScore W4320858396C137822555 @default.
- W4320858396 hasConceptScore W4320858396C143095724 @default.
- W4320858396 hasConceptScore W4320858396C144133560 @default.
- W4320858396 hasConceptScore W4320858396C151730666 @default.
- W4320858396 hasConceptScore W4320858396C151956035 @default.
- W4320858396 hasConceptScore W4320858396C15744967 @default.
- W4320858396 hasConceptScore W4320858396C199521495 @default.
- W4320858396 hasConceptScore W4320858396C2777267654 @default.
- W4320858396 hasConceptScore W4320858396C2781460075 @default.
- W4320858396 hasConceptScore W4320858396C38652104 @default.
- W4320858396 hasConceptScore W4320858396C41008148 @default.
- W4320858396 hasConceptScore W4320858396C77088390 @default.
- W4320858396 hasConceptScore W4320858396C77805123 @default.
- W4320858396 hasConceptScore W4320858396C86803240 @default.
- W4320858396 hasLocation W43208583961 @default.
- W4320858396 hasOpenAccess W4320858396 @default.
- W4320858396 hasPrimaryLocation W43208583961 @default.
- W4320858396 hasRelatedWork W1511063565 @default.
- W4320858396 hasRelatedWork W2264966880 @default.
- W4320858396 hasRelatedWork W2272748687 @default.
- W4320858396 hasRelatedWork W2412189159 @default.
- W4320858396 hasRelatedWork W2807420283 @default.
- W4320858396 hasRelatedWork W3119089187 @default.
- W4320858396 hasRelatedWork W3121708497 @default.
- W4320858396 hasRelatedWork W597761466 @default.
- W4320858396 hasRelatedWork W77105191 @default.
- W4320858396 hasRelatedWork W2134920304 @default.
- W4320858396 isParatext "false" @default.
- W4320858396 isRetracted "false" @default.
- W4320858396 workType "article" @default.