Abstract
Underground mining operations are increasingly dependent on autonomous vehicles, robotic drilling systems, and intelligent inspection platforms operating in confined, GPS-denied tunnel environments. These systems rely on distributed perception models to interpret navigation cues, hazard warnings, and environmental signals in real time. While centralized deep learning can enhance model performance, transferring raw operational data across mining sites introduces serious confidentiality and security risks. Federated Learning (FL) offers a privacy-preserving alternative by enabling collaborative model training without sharing local datasets. However, deploying FL in underground mining introduces several critical challenges: (i) Training labels may be modified either maliciously by compromised clients or inadvertently due to harsh underground conditions like such as low illumination or physical distortion of safety signs. Such alterations can result in label-flipping (LF) attacks, wherein corrupted semantic information propagates to the global model through poisoned local updates. (ii) Mining data is inherently heterogeneous and non-IID due to variations in tunnel shapes or uneven terrains, making malicious updates difficult to distinguish from natural distribution shifts. (iii) Underground communication networks are bandwidth-constrained, limiting the feasibility of computationally intensive cryptographic defenses or repeated validation procedures. To address these challenges, we propose TrustFed, a lightweight and unsupervised defense framework tailored for underground mining environments. TrustFed first filters client updates by detecting abnormal last-layer gradient norms and then performs clustering in gradient space to identify adversarial behavior. Clients are assigned adaptive trust scores based on their proximity to cluster centroids, and global aggregation is conducted using a soft trust-weighted mechanism that suppresses malicious contributions while preserving informative updates. To facilitate realistic evaluation, we further introduce MineSigns, a vision-based dataset capturing 13 safety-critical signage classes under authentic tunnel conditions, including low illumination and structural irregularities. Extensive experiments on MineSigns and standard benchmarks demonstrate that TrustFed effectively mitigates LF attacks and significantly improves global model robustness under both IID and non-IID mining scenarios. The code is available at : https://github.com/annonymousresearcher49/DEBS.
Recommended Citation
M. S. Rahman et al., "Label-Flip Attack Detection Via Trust-Weighted Aggregation In Federated Learning For Underground Mine Security," Debs 2026 Proceedings of the 20th ACM International Conference on Distributed and Event Based Systems, pp. 122 - 137, Association for Computing Machinery, Jun 2026.
The definitive version is available at https://doi.org/10.1145/3809481.3812617
Department(s)
Computer Science
Second Department
Mining Engineering
Publication Status
Open Access
Keywords and Phrases
autonomous mining; distributed learning security; event-driven systems; federated learning; label-flipping attacks; Non-IID data; trust-based aggregation
Document Type
Article - Conference proceedings
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 2026 The Author(s), All rights reserved.
Creative Commons Licensing
This work is licensed under a Creative Commons Attribution 4.0 License.
Publication Date
22 Jun 2026
