Jul 2026· International Journal of Engineering Research and Science & Technology· 0 citations
TL;DR
This work presents an intelligent approach for improving web application security through the prediction and detection of SQL injection attacks using machine learning techniques, enabling faster, more reliable, and automated detection of SQL injection vulnerabilities.
Abstract
Web applications have become an essential part of modern businesses, making them a common target for cyberattacks. Among various security threats, SQL injection remains one of the most dangerous because it allows attackers to manipulate database queries and gain unauthorized access to sensitive information. Traditional detection techniques often rely on predefined rules or signatures, which are less effective against newly emerging attack patterns. This work presents an intelligent approach for improving web application security through the prediction and detection of SQL injection attacks using machine learning techniques. The proposed framework processes SQL queries by performing data cleaning, feature extraction, and text preprocessing before training an ensemble classification model. The trained model distinguishes normal queries from malicious ones with high accuracy, enabling early identification of potential attacks. Performance is evaluated using standard metrics such as accuracy, precision, recall, and F1-score to verify the effectiveness of the system. The developed framework also provides a simple interface for analyzing new SQL queries and predicting their security status. This approach supports proactive protection of web applications by enabling faster, more reliable, and automated detection of SQL injection vulnerabilities.
The proposed machine learning-based system for detecting and mitigating SQL injection attacks is designed not just to protect against conventional SQLi attacks but also against JSON-based SQLi attacks, NoSQL injection attacks, hybrid attacks, and conventional WAF evasion techniques.
Nisha P. Shetty, Vinayak Kothari, Eva Hemantkumar Shah et al.· Journal of Mobile Multimedia· 0 citations
: Background: SQL injection is one of the cyberattacks which occurs in web application vulnerabilities. It targets the poor input validation and enables the attackers to inject malicious queries into the database fields in any application. It will grant access to unauthorized users and data modification, or they will take control over the complete database. To prevent this, there are several traditional methods, like Intrusion Detection Systems (IDS) and packet inspection methods, which will detect these attacks by each and every network packet in the network traffic. Methods: The existing methods also have some limitations due to computational overhead due to monitoring each and every packet. It makes it challenging for high-end routers and large-scale networks as it monitors all the individual traffic. To resolve this problem, propose a flow-based detection method, making use of lightweight protocols like NetFlow and sFlow to identify SQLI attacks. Unlike traditional methods, which require more inspection on individual packets, flow-based analysis uses mandatory communication metadata, like source and destination IP addresses, port numbers, etc. It minimizes the need for computationally expensive packet inspection, which is going to render the process of detection more trustworthy and economical, particularly within high-traffic conditions. Results: In order to validate this approach, we gathered two collections of data, which included net flow data of SQLI attacks of database systems such as SQL, postgres SQL, etc. It has both normal and bad traffic, and we applied machine learning models to the traffic. Conclusion: The results indicate that the proposed flow-based method is more efficient and scalable for detecting SQL injection attacks than packet-based inspection.
P. Vinoth, K. Sudar, S. Muthukumar· Journal of Computer Science· 0 citations
SQL injection (SQLI) remains a critical web application security threat, while conventional signature-based detection
methods face limitations in identifying evolving attack patterns and handling high-dimensional web request data. This study
proposes an improved machine learning framework for SQLI detection based on TF-IDF N-grams and Latent Dirichlet
Allocation (LDA). HTTP requests from the CSIC-2010 and ECML/PKDD-2007 datasets are processed to extract SQLI-related
traffic using SQL keyword-based filtering. TF-IDF trigram features are generated to represent request characteristics, followed
by LDA-based dimensionality reduction to obtain a compact latent semantic representation. Support Vector Machine (SVM) and
Random Forest (RF) classifiers are employed for classifying malicious and genuine requests. Experimental results demonstrate
the effectiveness of the proposed LDA-based approach. On the CSIC-2010 dataset, the SVM and RF models achieve 99.90% and
98.13% accuracy, respectively. On the ECML/PKDD-2007 dataset, the improved framework achieves 98.70% accuracy using
SVM and 99.85% using RF, with approximately 99% true-positive rate and mean ROC performance. The findings indicate that
LDA-based feature reduction can improve the effectiveness and efficiency of machine-learning-based SQLI detection.
Amit Hariyani· International Journal for Re...· 0 citations
The Android Malware Detection System provides a comprehensive, reliable, and user-friendly platform to safeguard mobile ecosystems against emerging threats, combining technical rigor with accessibility.
G. Vamsi, V. S. Vinay· International Scientific Jou...· 1 citation
Modern enterprise data repositories are increasingly subjected to sophisticated cyber-attacks, ranging from advanced SQL injection (SQLi) variants to insider data exfiltration. Traditional signature-based Intrusion Detection Systems (IDS) and static database auditing tools frequently fail against zero-day exploits and polymorphic threat vectors. This paper presents a comprehensive framework for database security threat detection utilizing hybrid Machine Learning (ML) methodologies. By combining supervised classification models for known attack signatures with unsupervised anomaly detection for behavioural drift, the proposed system analyses real-time Database Management System (DBMS) access logs, query structures, and session telemetry. The framework demonstrates a notable reduction in false-positive rates while maintaining high classification accuracy, bridging the gap between automated threat mitigation and database administration.
Jaishri D. Jatal· London Journal of Research i...· 0 citations
The findings confirm that an accessible, accurate, and AI-augmented vulnerability scanner can be constructed for educational and entry-level use within a deliberately bounded scope, lowering the expertise barrier for web application security assessment.
