Secure and Privacy-Preserving Federated Learning for Next-Generation Underground Mine Safety

2025-12-09

AI Summary

Underground mine safety monitoring relies on sensor data, yet centralized machine learning poses risks of privacy leakage and model attacks. To address this, we propose a decentralized federated learning framework tailored for mining environments. First, we introduce decentralized functional encryption (DFE)—a novel mechanism that ensures confidentiality of model updates and defends against model inversion and membership inference attacks. Second, we design a robust aggregation algorithm to mitigate convergence degradation caused by inter-mine Non-IID data distributions and sensor noise. Evaluated on a real-world mine dataset, our framework achieves 98.3% of the accuracy attained by centralized training, reduces communication overhead by 41%, and accelerates convergence by 2.3×. This work pioneers the integration of DFE into federated learning security architectures, unifying privacy preservation, adversarial robustness, and efficient collaborative modeling.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Data Mining & Knowledge Management: Scalability, Parallel & Distributed Systems
• Natural Language Processing: Safety and Robustness

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Security and Privacy: Security and privacy of machine learning and AI applications
• Systems and Infrastructure for Web, Mobile and WoT: Decentralized Web and Fediverse systems

Abstract

Underground mining operations depend on sensor networks to monitor critical parameters such as temperature, gas concentration, and miner movement, enabling timely hazard detection and safety decisions. However, transmitting raw sensor data to a centralized server for machine learning (ML) model training raises serious privacy and security concerns. Federated Learning (FL) offers a promising alternative by enabling decentralized model training without exposing sensitive local data. Yet, applying FL in underground mining presents unique challenges: (i) Adversaries may eavesdrop on shared model updates to launch model inversion or membership inference attacks, compromising data privacy and operational safety; (ii) Non-IID data distributions across mines and sensor noise can hinder model convergence. To address these issues, we propose FedMining--a privacy-preserving FL framework tailored for underground mining. FedMining introduces two core innovations: (1) a Decentralized Functional Encryption (DFE) scheme that keeps local models encrypted, thwarting unauthorized access and inference attacks; and (2) a balancing aggregation mechanism to mitigate data heterogeneity and enhance convergence. Evaluations on real-world mining datasets demonstrate FedMining's ability to safeguard privacy while maintaining high model accuracy and achieving rapid convergence with reduced communication and computation overhead. These advantages make FedMining both secure and practical for real-time underground safety monitoring.

Problem

• Secure FL for underground mining safety monitoring
• Privacy protection against model inversion and inference attacks
• Mitigating non-IID data and noise for convergence

Innovation

• Decentralized Functional Encryption for model privacy
• Balancing aggregation mechanism for data heterogeneity
• Reduced communication and computation overhead