Summary of A Systematic and Formal Study Of the Impact Of Local Differential Privacy on Fairness: Preliminary Results, by Karima Makhlouf et al.
A Systematic and Formal Study of the Impact of Local Differential Privacy on Fairness: Preliminary Results
by Karima Makhlouf, Tamara Stefanovic, Heber H. Arcolezi, Catuscia Palamidessi
First submitted to arxiv on: 23 May 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 A novel machine learning (ML) study investigates the impact of local differential privacy (DP) on fairness. The research focuses on understanding how varying levels of privacy affect the decisions made by ML models. The authors analyze the effect of local DP on fairness using bounds in terms of joint distributions and privacy level, identifying scenarios where privacy reduces discrimination and those where it exacerbates disparity. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A team of researchers looked into how a way to keep personal information private in machine learning affects the fairness of decisions made by these models. They found that this approach can have both positive and negative effects on fairness, depending on the level of privacy and the data being used. The study provides rules for when using this method will make decisions more fair and when it might actually make them less fair. |
Keywords
» Artificial intelligence » Machine learning
