Summary of Subword Embedding From Bytes Gains Privacy Without Sacrificing Accuracy and Complexity, by Mengjiao Zhang and Jia Xu
Subword Embedding from Bytes Gains Privacy without Sacrificing Accuracy and Complexity
by Mengjiao Zhang, Jia Xu
First submitted to arxiv on: 21 Oct 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
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 paper proposes a novel approach to protect privacy in federated learning against embedding attacks by encoding subwords into byte sequences using deep neural networks. The method, called Subword Embedding from Bytes (SEB), requires only 256 bytes of vocabulary memory while maintaining efficiency and accuracy. SEB outperforms conventional approaches in preserving privacy without sacrificing performance or results. The proposed solution shows promise in protecting against embedding-based attacks in federated learning, machine translation, sentiment analysis, and language modeling. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about finding a way to keep private information safe when using artificial intelligence models that learn from many different devices at the same time. Right now, these models can be used by attackers to get back the original text or data that was used to train them. To solve this problem, the researchers developed a new method called Subword Embedding from Bytes (SEB). SEB changes how words are represented in computer memory so it’s harder for attackers to get the original text back. The best part is that SEB doesn’t make the models work any slower or less accurately. |
Keywords
» Artificial intelligence » Embedding » Federated learning » Translation
