EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Ensemble Learning for SQL Injection Detection Using TF–IDF–Based Query Representation

Zain Wasef Marashdih, Mowafaq Salem Alzboon, Mohammad Subhi Al-Batah

Journal of Electrical and Computer Engineering · 2026-01 · 2026 (1)

DOI: 10.1155/jece/6089460 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Electrical and Computer Engineering, online erschienen am 08.11.2026. Verfasst von Zain Wasef Marashdih und 2 weiteren Autor:innen. Die Arbeit nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Structured Query Language Injection Attacks (SQLIAs) are among the most significant security threats to web applications, according to the Open Web Application Security Project (OWASP). These attacks enable unauthorized access to database information, compromising data security and application integrity. This study investigates machine learning (ML) models for SQLIA detection using a SQLIA dataset that was recently published on Kaggle. Textual queries were transformed into numerical features using term frequency–inverse document frequency (TF–IDF). To prevent data leakage, the dataset was first divided into training and testing subsets, and the TF–IDF vectorizer was fitted only on the training data before being applied to the test data. Random forest (RF), XGBoost, and an ensemble Voting Classifier were evaluated. In the experimental evaluation, 80% of the data was used for training and 20% for testing. Subsequently, experimental testing was conducted using 5‐fold cross‐validation. RF achieved the highest classification holdout accuracy of 99.48%, followed by the Voting Classifier with 99.41% and XGBoost with 99.39%. The Voting Classifier achieved the highest ROC–AUC score of 99.61%. These results indicate that TF–IDF–based query representation combined with ML models can provide effective SQLIA detection within the evaluated dataset. The findings highlight the importance of selecting appropriate classification models and robust validation strategies when dealing with high‐dimensional textual representations.

Zitieren

APA

Marashdih, Z. W., Alzboon, M. S., & Al-Batah, M. S. (2026). Ensemble Learning for SQL Injection Detection Using TF–IDF–Based Query Representation. Journal of Electrical and Computer Engineering, 2026(1). https://doi.org/10.1155/jece/6089460

Vancouver

Marashdih ZW, Alzboon MS, Al-Batah MS. Ensemble Learning for SQL Injection Detection Using TF–IDF–Based Query Representation. Journal of Electrical and Computer Engineering. 2026;2026(1). doi:10.1155/jece/6089460

BibTeX
@article{Marashdih2026,
  author = {Marashdih, Zain Wasef and Alzboon, Mowafaq Salem and Al-Batah, Mohammad Subhi},
  title = {Ensemble Learning for SQL Injection Detection Using TF–IDF–Based Query Representation},
  journal = {Journal of Electrical and Computer Engineering},
  year = {2026},
  volume = {2026},
  number = {1},
  doi = {10.1155/jece/6089460}
}
Kostenlos starten →