Summary of Anti-byzantine Attacks Enabled Vehicle Selection For Asynchronous Federated Learning in Vehicular Edge Computing, by Cui Zhang et al.
Anti-Byzantine Attacks Enabled Vehicle Selection for Asynchronous Federated Learning in Vehicular Edge Computing
by Cui Zhang, Xiao Xu, Qiong Wu, Pingyi Fan, Qiang Fan, Huiling Zhu, Jiangzhou Wang
First submitted to arxiv on: 12 Apr 2024
Categories
- Main: Machine Learning (cs.LG)
- 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 A federated learning approach is used in vehicle edge computing, where edge devices receive local models and update a global model. This reduces latency and allows for more efficient computation on varying amounts of local data, capabilities, and locations. However, Byzantine attacks can occur, affecting the accuracy of the system. A proposed deep reinforcement learning-based vehicle selection scheme takes into account mobility, channel conditions, computational resources, data amount, transmission status, and Byzantine attacks to eliminate poor-performing vehicles and focus on those with better performance. This improves the safety and accuracy of the global model. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In a world where cars talk to each other (vehicle edge computing), a new way of learning is used that helps reduce delays and makes it more efficient for different types of cars to work together. But sometimes, some cars might try to trick others or pretend they’re doing better than they are. To solve this problem, researchers created a new system that uses deep learning to help choose which cars are the best ones to listen to. This makes the overall system safer and more accurate. |
Keywords
* Artificial intelligence * Deep learning * Federated learning * Reinforcement learning
