New method enables privacy-preserving race/ethnicity fairness measurement

A new paper introduces Privacy-Preserving Probabilistic Race/Ethnicity Estimation (PPRE), a method designed to enable fairness measurements concerning race and ethnicity for LinkedIn members in the U.S. while maintaining privacy. PPRE integrates secure two-party computation, differential privacy, and additive homomorphic encryption with two distinct demographic signal sources. These sources include the Bayesian Improved Surname Geocoding estimator and a survey set of self-reported demographics, aiming to provide robust fairness metrics for candidate and viewer-side evaluations. The framework is presented as transferable for other institutions looking to build similar privacy-preserving measurement infrastructure. AI

IMPACT This research offers a framework for AI systems to measure fairness across demographic groups while adhering to strict privacy regulations.

RANK_REASON The cluster contains a research paper detailing a new methodology for fairness measurement. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• additive homomorphic encryption
• arXiv
• Bayesian Improved Surname Geocoding estimator
• differential privacy
• LinkedIn
• Osonde Osoba
• Privacy-Preserving Probabilistic Race/Ethnicity Estimation
• secure two-party computation
• U.S.

• paper
• safety

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →