Summary of A Unified Learn-to-distort-data Framework For Privacy-utility Trade-off in Trustworthy Federated Learning, by Xiaojin Zhang et al.
A Unified Learn-to-Distort-Data Framework for Privacy-Utility Trade-off in Trustworthy Federated Learning
by Xiaojin Zhang, Mingcong Xu, Wei Chen
First submitted to arxiv on: 5 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); 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 This paper introduces a theoretical foundation for the privacy-utility equilibrium in federated learning, based on Bayesian and total variation distance privacy definitions. The authors propose the “Learn-to-Distort-Data” framework, which models distortion introduced by privacy-preserving mechanisms as a learnable variable, optimizing it jointly with model parameters. This approach is demonstrated on various privacy-preserving mechanisms and connects to related areas like adversarial training, input robustness, and unlearnable examples. Techniques from these areas are used to design effective algorithms for achieving the privacy-utility equilibrium in federated learning. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps us understand how we can balance keeping data private with using it effectively in machine learning. It gives a new way to think about this problem by treating the changes made to the data as something that can be learned and optimized. This approach is useful for many different methods of protecting privacy, and it also connects to other important areas like making models more robust. |
Keywords
» Artificial intelligence » Federated learning » Machine learning
