Summary of Privacy-preserving Race/ethnicity Estimation For Algorithmic Bias Measurement in the U.s, by Saikrishna Badrinarayanan et al.
Privacy-Preserving Race/Ethnicity Estimation for Algorithmic Bias Measurement in the U.S
by Saikrishna Badrinarayanan, Osonde Osoba, Miao Cheng, Ryan Rogers, Sakshi Jain, Rahul Tandra, Natesh S. Pillai
First submitted to arxiv on: 6 Sep 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Cryptography and Security (cs.CR)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper proposes a novel approach to enabling AI fairness measurements on race/ethnicity for U.S. LinkedIn members in a privacy-preserving manner. The authors present the Privacy-Preserving Probabilistic Race/Ethnicity Estimation (PPRE) method, which combines the Bayesian Improved Surname Geocoding (BISG) model with sparse survey data and privacy-enhancing technologies like secure two-party computation and differential privacy. This approach enables meaningful fairness measurements while preserving member privacy. The paper provides details on the PPRE method’s privacy guarantees and illustrates sample measurement operations. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about making sure that AI systems treat people fairly, regardless of their race or ethnicity. The authors want to make it possible to measure this fairness without violating people’s privacy. They created a new way called PPRE (Privacy-Preserving Probabilistic Race/Ethnicity Estimation) that uses special techniques like secure math and hiding information to keep people’s personal details private. |
