An explainable machine learning-based web attack detection system for industrial IoT web application security

ABSTRACT

Within Industry 4.0, the integration of Industrial IoT (IIoT) marks a transformative phase for modern industries, fostering the development of smart factories and intelligent manufacturing systems. Despite the substantial growth of IIoT, a critical research gap persists in web security within IIoT environments. This paper addresses this gap by proposing an explainable and robust machine learning-based web attack detection system to ensure IIoT web application security using ToN-IoT and NF-ToN-IoTv2 datasets that accurately reflects IIoT traffic. Given eXplainable Artificial Intelligence’s (XAI) capability to instill trustworthiness and transparency in learning models, the authors opted for the SHAP technique for feature selection, leveraging its global insights to explain feature contributions to the system’s decision-making. Compared to the existing works, the system demonstrated strong performance across various metrics, including accuracy, recall, precision, specificity, F-value, FPR, FNR, AUC-ROC curve, MCE, training, and prediction times, in binary and multi-classification scenarios.

KEYWORDS:

• IIoT web application
• Industry 4.0
• machine learning
• web security

Disclosure statement

No potential conflict of interest was reported by the author(s).

Data availability statement

The authors declare that the dataset used in the work, as well as the code, is available upon request from the corresponding author.

Additional information

Funding

The authors declare that this work did not receive support from any funding agency.