Summary of Fedprophet: Memory-efficient Federated Adversarial Training Via Theoretic-robustness and Low-inconsistency Cascade Learning, by Minxue Tang et al.
FedProphet: Memory-Efficient Federated Adversarial Training via Theoretic-Robustness and Low-Inconsistency Cascade Learning
by Minxue Tang, Yitu Wang, Jingyang Zhang, Louis DiValentin, Aolin Ding, Amin Hass, Yiran Chen, Hai “Helen” Li
First submitted to arxiv on: 12 Sep 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
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 explores Federated Learning (FL) and Federated Adversarial Training (FAT) to achieve strong privacy guarantees and robustness against adversarial examples. FL enables local training on edge devices without sharing data, while FAT enhances robustness further. However, existing methods require large models, which are impractically slow for memory-constrained edge devices. The paper proposes a novel approach that addresses objective inconsistency between local and global models to achieve better accuracy and robustness in FAT. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps make artificial intelligence more trustworthy by protecting privacy and making sure it works well even when someone tries to trick it. It does this by using special training methods on devices like smartphones or smart home appliances, without sharing the data they use. However, these methods are currently too slow for some devices. The researchers came up with a new idea that should help make them faster and more accurate. |
Keywords
» Artificial intelligence » Federated learning
