Decentralized Trust for Space AI: Blockchain-Based Federated Learning Across Multi-Vendor LEO Satellite Networks

2025-12-09

AI Summary

To address intermittent connectivity, malicious update injection, and cross-vendor trust deficits in low-Earth-orbit (LEO) satellite-based federated learning (FL), this paper proposes OrbitChain—a blockchain-augmented FL framework. Its core innovation is the first-ever offloading of blockchain consensus to high-altitude platforms (HAPs), enabling lightweight, low-latency, auditable, and traceable model updates across orbital layers and vendor domains. OrbitChain introduces a tamper-resistant aggregation mechanism to enhance global model robustness against adversarial attacks. Integrating a permissioned proof-of-authority (PoA) blockchain, HAP-coordinated computation, and realistic satellite communication modeling, the framework ensures privacy and security while achieving a 30-hour reduction in convergence time, sub-160-ms block confirmation latency, and significantly lower communication and computational overhead. Experimental results demonstrate substantial improvements in model accuracy, trustworthiness, and resilience to Byzantine and data-poisoning attacks.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Search and Optimization: Distributed Search
• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust

Application Category

• Security and Privacy: Blockchains and distributed ledgers
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

The rise of space AI is reshaping government and industry through applications such as disaster detection, border surveillance, and climate monitoring, powered by massive data from commercial and governmental low Earth orbit (LEO) satellites. Federated satellite learning (FSL) enables joint model training without sharing raw data, but suffers from slow convergence due to intermittent connectivity and introduces critical trust challenges--where biased or falsified updates can arise across satellite constellations, including those injected through cyberattacks on inter-satellite or satellite-ground communication links. We propose OrbitChain, a blockchain-backed framework that empowers trustworthy multi-vendor collaboration in LEO networks. OrbitChain (i) offloads consensus to high-altitude platforms (HAPs) with greater computational capacity, (ii) ensures transparent, auditable provenance of model updates from different orbits owned by different vendors, and (iii) prevents manipulated or incomplete contributions from affecting global FSL model aggregation. Extensive simulations show that OrbitChain reduces computational and communication overhead while improving privacy, security, and global model accuracy. Its permissioned proof-of-authority ledger finalizes over 1000 blocks with sub-second latency (0.16,s, 0.26,s, 0.35,s for 1-of-5, 3-of-5, and 5-of-5 quorums). Moreover, OrbitChain reduces convergence time by up to 30 hours on real satellite datasets compared to single-vendor, demonstrating its effectiveness for real-time, multi-vendor learning. Our code is available at https://github.com/wsu-cyber-security-lab-ai/OrbitChain.git

Problem

• Ensures trustworthy federated learning across multi-vendor LEO satellite networks
• Prevents biased or falsified model updates from affecting global aggregation
• Reduces convergence time and overhead in intermittent connectivity environments

Innovation

• Blockchain-backed framework for trustworthy multi-vendor collaboration
• Offloads consensus to high-altitude platforms for computational efficiency
• Ensures transparent auditable provenance of model updates across orbits