Summary of Blockchain-enabled Trustworthy Federated Unlearning, by Yijing Lin et al.
Blockchain-enabled Trustworthy Federated Unlearning
by Yijing Lin, Zhipeng Gao, Hongyang Du, Jinke Ren, Zhiqiang Xie, Dusit Niyato
First submitted to arxiv on: 29 Jan 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 This paper proposes a novel blockchain-enabled framework for trustworthy federated unlearning, addressing the “right to be forgotten” issue in machine learning. By designing a proof of federated unlearning protocol and an adaptive contribution-based retraining mechanism, the authors demonstrate improved training efficiency and better data removal effects compared to state-of-the-art frameworks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Federated unlearning is a way to protect people’s data when they’re using machine learning models together with others. It helps make sure that old information is forgotten, which is important for privacy. The problem is that some current methods keep track of what each person contributed, even after they stop helping. To fix this, the researchers created a new system that uses blockchain technology to verify that data is removed and not kept by anyone else. They also developed a way to retrain the models without using too much computer power. The results show that their method works better than others do. |
