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.