Summary of Epic: Enhancing Privacy Through Iterative Collaboration, by Prakash Chourasia et al.
EPIC: Enhancing Privacy through Iterative Collaboration
by Prakash Chourasia, Heramb Lonkar, Sarwan Ali, Murray Patterson
First submitted to arxiv on: 7 Nov 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 proposed Privacy enhancement through Iterative Collaboration (EPIC) architecture tackles the challenges of training powerful deep learning models on sensitive genomic sequence data by employing Federated Learning (FL). This approach enables distributed learning, allowing multiple stakeholders to contribute their data while maintaining privacy. The EPIC framework is demonstrated for a supervised classification task estimating SARS-CoV-2 genomic sequence data lineage without sharing raw sequence data. By leveraging FL and iterative collaboration, the architecture achieves accurate predictions while preserving data confidentiality. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Machine learning helps scientists analyze viral sequences like COVID-19’s. Traditionally, this requires collecting lots of data in one place, which is hard to do when it comes to healthcare. It’s also a privacy concern because patients’ data should be kept private. To solve these issues, researchers developed a new way called Federated Learning (FL). This approach allows different groups to work together on training models while keeping their data private. The team proposed an EPIC architecture that splits the process between local and centralized servers. They tested this idea by predicting the lineage of COVID-19 sequences without sharing the actual sequences. They want to create a system where multiple groups can work together to train better models. |
Keywords
» Artificial intelligence » Classification » Deep learning » Federated learning » Machine learning » Supervised
