Detecting Untargeted Attacks and Mitigating Unreliable Updates in Federated Learning for Underground Mining Operations

2025-08-13

AI Summary

Underground mining federated learning faces dual challenges: malicious model attacks (e.g., sign-flipping, noise injection) and unreliable local updates stemming from low-quality data (e.g., poor illumination, sensor inaccuracies). To address these, we propose MineDetect—a novel framework featuring a history-aware gradient analysis mechanism. By modeling the historical distribution of local-to-global gradient updates, MineDetect distinguishes adversarial anomalies from data-quality-induced deviations, enabling joint defense against malicious models and suppression of unreliable updates. The framework integrates non-IID data handling with a lightweight architecture, ensuring compatibility with resource-constrained edge mining devices. Extensive experiments demonstrate that MineDetect significantly improves classification accuracy and robustness across diverse non-IID scenarios, while maintaining low computational overhead—outperforming state-of-the-art defense methods.

Technology Category

• Machine Learning: Adversarial Learning & Robustness
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Web Mining and Content Analysis: Web data provenance, reliability, and authenticity
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Underground mining operations rely on distributed sensor networks to collect critical data daily, including mine temperature, toxic gas concentrations, and miner movements for hazard detection and operational decision-making. However, transmitting raw sensor data to a central server for training deep learning models introduces significant privacy risks, potentially exposing sensitive mine-specific information. Federated Learning (FL) offers a transformative solution by enabling collaborative model training while ensuring that raw data remains localized at each mine. Despite its advantages, FL in underground mining faces key challenges: (i) An attacker may compromise a mine's local model by employing techniques such as sign-flipping attacks or additive noise, leading to erroneous predictions; (ii) Low-quality (yet potentially valuable) data, caused by poor lighting conditions or sensor inaccuracies in mines may degrade the FL training process. In response, this paper proposes MineDetect, a defense FL framework that detects and isolates the attacked models while mitigating the impact of mines with low-quality data. MineDetect introduces two key innovations: (i) Detecting attacked models (maliciously manipulated) by developing a history-aware mechanism that leverages local and global averages of gradient updates; (ii) Identifying and eliminating adversarial influences from unreliable models (generated by clients with poor data quality) on the FL training process. Comprehensive simulations across diverse datasets demonstrate that MineDetect outperforms existing methods in both robustness and accuracy, even in challenging non-IID data scenarios. Its ability to counter adversarial influences while maintaining lower computational efficiency makes it a vital advancement for improving safety and operational effectiveness in underground mining.

Problem

• Detecting untargeted attacks in Federated Learning for mining operations
• Mitigating unreliable updates from low-quality mining sensor data
• Ensuring privacy and robustness in underground mining FL systems

Innovation

• History-aware gradient update mechanism
• Detects and isolates attacked models
• Mitigates low-quality data impact