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

TL;DR

This paper introduces MineDetect, a federated learning framework that detects and isolates malicious or low-quality data sources in underground mining sensor networks, enhancing model robustness and data privacy.

Contribution

MineDetect presents novel mechanisms for identifying attacked and unreliable models in federated learning for underground mining, improving robustness against adversarial attacks and data quality issues.

Findings

MineDetect effectively detects malicious models with high accuracy.

It mitigates the impact of low-quality data on model training.

Outperforms existing defenses in robustness and accuracy in simulations.

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.