MUMBAI, India, July 13 -- Intellectual Property India has published a patent application (202641084201 A) filed by Vallurupalli Nageswara Rao Vignana Jyothi Institute Of Engineering Technology on July 09, 2026, for Andrews Curve-Enhanced Spectral Ddos Detection System For Real-Time Network Traffic Classification.
Inventors include Dr. Vangipuram Radhakrishna; V. Sravan Kiran; Dr. Annaluri Sreenivasa Rao; Dr. N. Mangathayaru; Bibireddy Aashritha; and Billakanti Krishna Sai.
The application for the patent was published on July 10, 2026, under issue no. 28/2026.
Abstract: The present invention relates to a method and system for detecting and classifying Distributed Denial-of-Service (DDoS) attacks using network flow data. Network flow records are acquired from packet-capture-derived flow records, stored datasets, or live network sources and are subjected to preprocessing to remove non-informative, redundant, constant valued, and correlated features. Statistically significant flow features are selected and normalized to generate standardized feature representations. The normalized features are transformed into Andrews curve representations, wherein a plurality of Andrews curve values are generated and arranged in matrix form. Spectral-domain analysis is performed on the Andrews curve representation to generate magnitude spectrum features and phase spectrum features. The generated spectral features are augmented with selected network flow features to form enhanced feature vectors. The enhanced feature vectors are processed by a machine learning-based classification engine to classify network traffic as benign traffic, DDoS attack traffic, low-rate DDoS traffic, high-rate DDoS traffic, or combinations thereof, thereby improving network attack detection performance and security monitoring.
Disclaimer: Curated by HT Syndication.
