MUMBAI, India, July 24 -- Intellectual Property India has published a patent application (202641081584 A) filed by Vallurupalli Nageswara Rao Vignana Jyothi Institute Of Engineering Technology on July 02, 2026, for Real-Time Ddos Detection System Using Sequential Statistical Feature Selection And Dense Multi-Layer Perceptron Classification.
Inventors include Dr. V. Radhakrishna; Manthena Raghupathi; and Dr. P. Aparna.
The application for the patent was published on July 17, 2026, under issue no. 29/2026.
Abstract: The present invention relates to a system and method for detecting Distributed Denial-of-Service (DDoS) attacks in communication networks using sequential statistical feature optimization and machine learning. The system comprises a network traffic collector, a preprocessing module, a feature optimization module, a machine learning module, and a detection module. The feature optimization module performs a two-stage statistical feature selection process comprising a first-stage deviation-based filtering based on statistical deviation measures and a second-stage dependency-based filtering based on statistical association between feature values and classification labels, thereby generating a reduced and discriminative feature subset from high-dimensional network traffic data. The selected features are utilized by the machine learning module to train a neural network classifier, which is deployed in the detection module for real-time classification of network traffic into benign and DDoS attack traffic. The invention reduces computational complexity and improves detection accuracy in high-throughput network environments.
Disclaimer: Curated by HT Syndication.
