MUMBAI, India, June 26 -- Intellectual Property India has published a patent application (202641052492 A) filed by Hindusthan College Of Engineering And Technology on April 24, 2026, for Ai Driven Next Generation Firewall For Dynamic Threat Detection And Zero Trust Implementation.
Inventors include Athira S; Merlin Swetha R; Pritheev S; Siva M; and Vetrichelvan R.
The application for the patent was published on June 19, 2026, under issue no. 25/2026.
Abstract: BSTRACT OF THE INVENTION: With the rapid growth of internet usage and cloud-based services, network infrastructures are increasingly exposed to sophisticated cyber-attacks such as Distributed Denial of Service (DDoS), brute force attacks, botnets, and infiltration attempts. Traditional signature-based intrusion detection systems often fail to detect zero-day and evolving threats. To address this challenge, this project presents a Machine Learning-based Anomaly Detection System using the CTCIDS2019 dataset for accurate and real-time network traffic analysis. The proposed system implements five supervised machine learning algorithms Random Forest, Gradient Boosting, Support Vector Machine (SVM), Logistic Regression, and K-Nearest Neighbors to perform binary classification of network traffic into normal and anomalous categories. Feature scaling and preprocessing techniques are applied to improve model performance, and crossvalidation is used to ensure generalization. Among the evaluated models. Gradient Boosting achieved detection based on the highest binary classification accuracy of 98.32%, demonstrating superior capability. In addition to binary classification, a multi-class classification model Random Forest is trained to identify specific attack types. The system integrates majority voting across models to enhance prediction robustness and reduce false positives. A user-friendly web interface is developed using Streamlit to enable real-time single and batch traffic analysis, visualization of model confidence scores, attack type probability distributions, feature importance analysis, and prediction history tracking. The experimental results indicate that the proposed ensemble-based IDS framework provides high detection accuracy, reliable attack classification, and efficient real-time performance. This system demonstrates the effectiveness of machine learning techniques in strengthening modern cybersecurity infi*astructures and mitigating network-based threats
Disclaimer: Curated by HT Syndication.
