对比星群安全的集中与分散管理，提出三类AI架构方案
Centralized vs. Decentralized Security for Space AI Systems? A New Look
- 分三类AI架构：集中式、分布式、联邦式
- 短期看集中式训练快，长期看分散式更可扩展且安全
- 适合关注太空AI系统安全设计的研究者
本文研究卫星星座中集中式与去中心化安全管理之间的权衡，以平衡安全与性能。我们提出了三种用于自动化安全管理的AI架构：(a) 集中式，(b) 分布式，(c) 联邦式。短期内，集中式架构是更优选择，尽管存在跨空间通信延迟带来的挑战；长期来看，去中心化架构在可扩展性和安全性方面更具优势。
原文摘要 · Abstract (English)
This paper investigates the trade-off between centralized and decentralized security management in constellations of satellites to balance security and performance. We highlight three key AI architectures for automated security management: (a) centralized, (b) distributed and (c) federated. The centralized architecture is the best option short term, providing fast training, despite the hard challenge of the communication latency overhead across space. Decentralized architectures are better alternatives in the longer term, providing enhanced scalability and security.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。