Summary of Tangent Differential Privacy, by Lexing Ying
Tangent differential privacy
by Lexing Ying
First submitted to arxiv on: 6 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Cryptography and Security (cs.CR); Machine Learning (stat.ML)
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 This research note proposes a novel form of differential privacy called tangent differential privacy. Unlike traditional differential privacy, which defines uniform protection across data distributions, tangent differential privacy is tailored to a specific data distribution of interest. This approach also accommodates various distribution distances, such as total variation distance and Wasserstein distance. The study demonstrates that entropic regularization can guarantee tangent differential privacy for risk minimization under general conditions on the risk function. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research paper introduces a new way to keep individual data private called “tangent differential privacy”. It’s different from regular methods because it’s designed specifically for certain types of data. The method also works with different measures of how far apart two datasets are. In a real-world application, the researchers show that using “entropic regularization” can make sure this new method is effective. |
Keywords
» Artificial intelligence » Regularization
