MUMBAI, India, May 29 -- Intellectual Property India has published a patent application (202641061613 A) filed by Nri Institute Of Technology; Mr. V. Dhanush; Mr. P. Karthikeya; Mr. P. Komal Kalyan; Mr. P. Trinadh; and Mr. G. Siva Sankara Rao, Eluru, Andhra Pradesh, on May 14, for 'network-aware hybrid deep learning system for intrusion detection on labelled and unlabelled traffic data.'
Inventor(s) include Mr. V. Dhanush; Mr. P. Karthikeya; Mr. P. Komal Kalyan; Mr. P. Trinadh; and Mr. G. Siva Sankara Rao.
The application for the patent was published on May 29, under issue no. 22/2026.
According to the abstract released by the Intellectual Property India: "The invention here discloses a hybrid software-based network intrusion detection system that utilizes machine learning and deep learning to evaluate labeled and unlabeled network traffic data. The invention utilizes benchmark-style records of network connections that are given descriptive attribute names and undergo a pre-processing routine that normalizes numerical attributes, one-hot encodes categorical attributes, and transforms original labels into binary and multi-class categories of network intrusions. The invention utilizes correlation-based feature selection to create compact datasets that perform binary and multi-class classification. The invention utilizes this dataset to train an ensemble of machine learning models that include Random Forests, Support Vector Machines, k-Nearest Neighbors, discriminant analysis-based models, Multi-Layer Perceptron, Convolutional Neural Networks, Long Short-Term Memory networks, and Autoencoders to perform network intrusion detection. The invention also produces performance metrics and label visualizations that are intended to be integrated into live network environments to create an adaptive approach to network security."
Disclaimer: Curated by HT Syndication.
