Summary of Federated Knowledge Recycling: Privacy-preserving Synthetic Data Sharing, by Eugenio Lomurno et al.
Federated Knowledge Recycling: Privacy-Preserving Synthetic Data Sharing
by Eugenio Lomurno, Matteo Matteucci
First submitted to arxiv on: 30 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
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 approach to federated learning called Federated Knowledge Recycling (FedKR) is proposed, addressing privacy and security concerns by utilizing synthetic data generated locally at institutions. FedKR combines advanced data generation techniques with a dynamic aggregation process to reduce the attack surface and provide greater security against privacy attacks. Experimental results demonstrate competitive performance on various datasets, achieving an average improvement in accuracy of 4.24% compared to training models from local data. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Federated learning helps many institutions work together without sharing their sensitive data. But current methods have some big weaknesses that make them vulnerable to attacks. A new approach called Federated Knowledge Recycling (FedKR) makes things safer by using fake data created locally at each institution. This reduces the risk of privacy breaches and keeps the sensitive information safe. The results show that FedKR works well, improving accuracy by 4.24% compared to just training on local data. |
Keywords
» Artificial intelligence » Federated learning » Synthetic data
