Development of a machine learning model for automatic detection of SQL injections in web applications of the construction industry
How to cite
Abstract
The digital transformation of the construction industry has led to a significant increase in the number of specialized web applications that process confidential data on projects, estimates, and logistical resources. These systems are becoming an attractive target for cyber attacks, among which SQL injections remain one of the most dangerous and widespread threats. This study is devoted to the development and evaluation of the effectiveness of a machine learning model for the automatic detection of SQL injections in the web applications of the construction industry. The work uses an integrated approach that includes collecting a unique data set from 15,863 queries to industry-specific construction project management systems, in-depth analysis of the syntactic and semantic features of malicious code specific to this industry, and the creation of a multi-level classification model based on random forest and deep learning algorithms. The developed model demonstrated high accuracy (97.8%) in detecting malicious requests, including complex polymorphic attacks aimed at extracting data on construction projects, suppliers, and financial transactions. The uniqueness of the proposed solution lies in the adaptation of natural language vectorization to the specific context of construction documentation and the integration of industry knowledge into the neural network architecture. The results of field testing on existing construction management systems confirmed a 43.2% reduction in false alarms compared to traditional intrusion detection systems. The proposed approach has practical value for ensuring cybersecurity of the digital ecosystem of construction organizations and can be integrated into existing industry solutions.
Keywords
References
Alghawazi M., Alghazzawi D., Alarifi S. Detection of SQL injection attack using machine learning techniques: a systematic literature review // Journal of cybersecurity and privacy. 2022. Vol. 2. № 4. pp. 764-777.
Boehm W., Chung F. Building Information Modeling (BIM) and Cybersecurity: A Study on Protecting Sensitive Building Information // Journal of information technology in construction. 2021. Vol. 26. рр. 159-173.
Chen Z. Improving Vulnerability Detection Using Deep Learning and Semantic Analysis on Source Code // IEEE 19th Intern. сonf. on software quality, reliability and security. 2019. рр. 410-417.
Demilie W.B., Deriba F.G. Detection and prevention of SQLI attacks and developing compressive framework using machine learning and hybrid techniques // Journal of Big Data. 2022. Vol. 9. № 124.
Falor A. A deep learning approach for detection of sql injection attacks using convolutional neural networks // Lecture notes on data engineering and communications technologies. 2022. Vol. 91.
Li J. Deep learning-based detection technology for SQL injection research and implementation // Applied sciences. 2023. Vol. 13. № 16. рр. 66-94.
Li Q. LSTM-based SQL injection detection method for intelligent transportation system // IEEE Transactions on Vehicular Technology. 2019. Vol. 68. № 5. pp. 4182-4191.
Liu T. Deep Learning in Cybersecurity: A Hybrid BERT–LSTM Network for SQL Injection Attack Detection // IET Information security. 2024.
Mantha B.R., de Soto B.G. Cyber security challenges and vulnerability assessment in the construction industry // Proceedings of the сreative сonstruction сonf. 2019. рр. 29-36.
McWhirter P.R. SQL Injection Attack classification through the feature extraction of SQL query strings using a gap-weighted string subsequence kernel // Journal of information security and applications. 2018. Vol. 40. рр. 199-216.
Nawari N.O., Ravindran S. Blockchain and the built environment: Potentials and limitations // Journal of Building Engineering. 2019. Vol. 25.
Pаrn E.A., Edwards D.J. Cyber threats confronting the digital built environment: Common data environment vulnerabilities and block chain deterrence // Engineering, construction and architectural management. 2019. Vol. 26. № 2. рр. 245-266.
Tang P. Detection of SQL injection based on artificial neural network // Knowledge-based systems. 2020. Vol. 190.
Uwagbole S.O., Buchanan W.J., Fan L. Applied machine learning predictive analytics to SQL injection attack detection and prevention // IFIP/IEEE Symposium on integrated network and service management. 2017.
Zhang W. Deep Neural Network-Based SQL Injection Detection Method // Security and communication networks. 2022.