MUMBAI, India, July 7 -- Intellectual Property India has published a patent application (202641081062 A) filed by Malla Reddy Engineering College Women Autonomous; Malla Reddy University; Malla Reddy Mr Deemed To Be University; and Malla Reddy Vishwavidyapeeth Deemed on July 01, 2026, for Ai-Based Network Intrusion Detection System For Anomaly Detection Using Nsl-Kdd Dataset.
Inventors include Dr. Y. Madhaveelatha; Mr. Sai Krishna Goud Nemuri; Ms. M. Maheswari; Mr. Rajesh Shine Dhasaian; Mr. Venkatesh Kummari; Dr. Nenavath Chander; Mr. Pilli Uday; and Dr. Kanaka Durga Returi.
The application for the patent was published on July 03, 2026, under issue no. 27/2026.
Abstract: The rapid growth of digital networks has significantly increased the risk of cyber threats, making network security a critical concern for organizations and individuals. Traditional Intrusion Detection Systems (IDS), which rely on signature-based techniques, are often ineffective against zero-day attacks and evolving cyber threats. To address these limitations, this project proposes an AI-based Network Intrusion Detection System (NIDS) that detects anomalies in network transmission and identifies potential cyberattacks with high accuracy. The proposed system utilizes the NSL-KDD dataset for training and evaluation, ensuring reliable and balanced data representation. Advanced machine learning algorithms such as Support Vector Machine (SVM), Random Forest, Logistic Regression, and ensemble methods like Voting and Stacking classifiers are implemented to classify network traffic into normal and attack categories, including DoS, Probe, Remote-to-Local (R2L), and User-to-Root (U2R) attacks. Dimensionality reduction techniques such as Principal Component Analysis (PCA) are applied to improve model efficiency and reduce overfitting. The system follows a structured pipeline including data preprocessing, feature engineering, model training, evaluation, and deployment using a Flask-based web interface. Performance is evaluated using metrics such as accuracy, precision, recall, F1-score, and ROC-AUC, ensuring reliable detection with reduced false positives. Additionally, Explainable AI techniques are incorporated to enhance transparency and trust in decision-making. The developed system provides a cost-effective, scalable, and efficient cybersecurity solution capable of detecting network anomalies in real-time or batch processing environments. It reduces manual monitoring effort, improves threat response time, and supports proactive security measures. This project contributes to strengthening digital security infrastructure and demonstrates the practical application of artificial intelligence in modern cybersecurity systems
Disclaimer: Curated by HT Syndication.
