🤖 AI Summary
This study addresses the dual challenges of benign heterogeneity—arising from diverse operating conditions and failure modes—and adversarial heterogeneity caused by malicious poisoning attacks in federated learning for aircraft engine remaining useful life prediction. To enhance both accuracy and security while preserving the privacy of raw sensor data, the work integrates personalized federated learning with robust aggregation mechanisms. It innovatively introduces a physics-informed sensor backdoor attack and presents the first systematic evaluation of the synergy between shared representation personalization and robust aggregators such as Krum. Experimental results demonstrate that shared representation personalization reduces the performance gap between local and centralized models by 70%, while Krum suppresses attack success rates from 94.9% to 2.8%, achieving high predictive accuracy alongside significantly improved robustness.
📝 Abstract
Federated learning (FL) enables aircraft fleet operators to jointly train remaining-useful-life (RUL) models from engine sensor telemetry without sharing raw data. This study examines two complementary challenges: benign heterogeneity, where honest operators observe different operating conditions and fault modes, and adversarial heterogeneity, where compromised operators submit poisoned updates. We conduct a controlled, safety-oriented evaluation using a multi-task one-dimensional convolutional neural network and a structurally non-IID partition of the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) benchmark. We compare four remedies for benign heterogeneity and evaluate five attacks against four aggregation methods, including a physically motivated sensor-value backdoor designed to mask engine degradation.
Shared-representation personalization closes approximately 70% of the local-to-centralized root-mean-square-error gap, compared with 21% for proximal regularization and 10% for server-side reweighting. The backdoor achieves a 94.9% attack success rate against standard averaging while leaving clean accuracy statistically unchanged, demonstrating that accuracy alone cannot certify model safety and that attack success must be evaluated explicitly. Krum reduces attack success by an order of magnitude and is the only evaluated aggregator that withstands coordinated attackers, whereas personalization alone provides no protection. Combining personalization with robust aggregation restores robustness (2.8% attack success) with only a small accuracy cost, revealing a trade-off between robust update selection and collaborative representation learning. Results remain consistent across client counts and on a harder six-condition dataset. Code and data partitions are released for reproducibility.