Summary of Random Gradient Masking As a Defensive Measure to Deep Leakage in Federated Learning, by Joon Kim et al.
Random Gradient Masking as a Defensive Measure to Deep Leakage in Federated Learning
by Joon Kim, Sejin Park
First submitted to arxiv on: 15 Aug 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 investigates the effectiveness of four defensive methods against Deep Leakage from Gradients (DLG) attacks in Federated Learning (FL). The methods, including Masking, Clipping, Pruning, and Noising, are evaluated on MNIST, CIFAR-10, and lfw datasets to determine their minimum hyperparameter threshold for defense. The results show that Masking and Clipping exhibit near-zero degradation in performance while successfully obfuscating information to prevent DLG attacks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper looks at ways to protect individual data privacy in Federated Learning (FL). FL is a way for machines to learn together without sharing their private data. But, there are bad guys called Deep Leakage from Gradients (DLG) that can steal this data. To stop them, the authors tested four methods: Masking, Clipping, Pruning, and Noising. They found out that one of these methods, Masking, works really well at keeping data private while still letting machines learn. |
Keywords
» Artificial intelligence » Federated learning » Hyperparameter » Pruning
