Application of Differential Privacy to Sensor Data in Water Quality Monitoring Task
Ecological Informatics 2025
Audris Arzovs, Sergejs Paršutins, Valts Urbanovičs, Jānis Rubulis, Sandis Dejus

Although differential privacy (DP) is used to obfuscate local information and avoid data leakage, very little research exists on the neural network model performance with applied DP for datasets from online drinking water sensor monitoring. This study aims to examine the accuracy of four different neural network model architectures with DP applications. To compare the performance of the neural network model performance in total 2 215 906 augmented and experimentally obtained sensor readings were obtained from a drinking-water pilot system. Three types of contaminations at three different concentrations were applied as scenarios for anomalies in drinking water monitoring. The results achieved similar accuracy with all model architectures, with the best result showing only a 0.3% reduction in model accuracy compared with a nonprivate neural network model with 94% and 94.7% accuracy, respectively. Thus, differential privacy can be applied in the field of water quality monitoring with a reasonable decrease in the model performance.


Keywords
Water quality monitoring, Differential privacy, Federated learning
DOI
10.1016/j.ecoinf.2025.103019
Hyperlink
https://www.sciencedirect.com/science/article/pii/S1574954125000287?via%3Dihub

Arzovs, A., Paršutins, S., Urbanovičs, V., Rubulis, J., Dejus, S. Application of Differential Privacy to Sensor Data in Water Quality Monitoring Task. Ecological Informatics, 2025, Vol. 86, pp.1-11. ISSN 1574-9541. e-ISSN 1878-0512. Available from: doi:10.1016/j.ecoinf.2025.103019

Publication language
English (en)
The Scientific Library of the Riga Technical University.
E-mail: uzzinas@rtu.lv; Phone: +371 28399196