POTLAKAYALA SUDHARSANA RAO , VASUPALLI ABHISHEK2, OMMI NIKHIL KUMAR3, RAYAVARAPU PAVAN KUMAR 4,CHEMBU MANOHAR5 03 3(1) SQL Injection SQLi remains one of the most prevalent and destructive threats to modern web applications enabling adversaries to bypass authentication exfiltrate sensitive data and compromise entire backend systems Conventional countermeasures such as Web Application Firewalls WAFs and signaturebased filters depend on static rule sets that are ineffective against obfuscated polymorphic or zeroday payloads This paper presents an adaptive datadriven detection framework that leverages Term FrequencyInverse Document Frequency TFIDF feature extraction coupled with a Random Forest classifierarchitected for straightforward migration to Artificial Neural Networks ANNto accurately distinguish malicious from benign SQL queries The system is deployed as a fullstack web application a Flaskbased REST API exposes a predict endpoint for realtime classification SQLite manages user credentials through bcrypthashed storage and a responsive HTMLCSSJavaScript interface surfaces actionable security alerts Comprehensive evaluation using accuracy precision recall and F1score demonstrates that the proposed approach substantially outperforms rulebased baselines while maintaining subsecond inference latency The modular architecture supports seamless substitution of the classifier with LSTM or CNN models as threat landscapes evolve Copyright (c) Journal of Science Engineering Technology and Management Science. All rights reserved 2026