Summary of On the Conflict Of Robustness and Learning in Collaborative Machine Learning, by Mathilde Raynal and Carmela Troncoso
On the Conflict of Robustness and Learning in Collaborative Machine Learning
by Mathilde Raynal, Carmela Troncoso
First submitted to arxiv on: 21 Feb 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 In this paper, researchers propose Collaborative Machine Learning (CML) as a solution to privacy issues in applications like healthcare. To ensure reliable decisions, they suggest using robust aggregators to filter out malicious contributions that can negatively impact training. The authors formalize two prevalent forms of robust aggregators and show that neither provides the intended protection, either failing to identify malicious inputs or preventing learning without eliminating risk. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Collaborative Machine Learning (CML) helps people share models while keeping their data private. This is important for healthcare and other applications where safety matters. To keep models safe from bad influences, researchers use robust aggregators to filter out harmful contributions. In this paper, the authors explain two types of robust aggregators that aren’t effective at solving these problems. |
Keywords
* Artificial intelligence * Machine learning
