MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122992 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 5, 2025, for 'deep learning autoencoder system for iot network anomaly detection.'
Inventor(s) include Anuprabha S S; R. Tejaswini; P. Abinaya; Dr. Sudhanshu Arya; Dr. Yogesh Kumar Choukiker; and Dr. Abhijit Bhowmick.
The application for the patent was published on Jan. 2, under issue no. 01/2026.
According to the abstract released by the Intellectual Property India: "The present disclosure provides a deep learning autoencoder system for IoT network anomaly detection. The system includes a convolutional neural network-based autoencoder configured to receive IoT network traffic data and process it through an encoding phase with convolutional layers for feature extraction and dimensionality reduction to generate a latent representation, and a decoding phase for reconstructing the data from the latent representation. A Random Forest classifier receives encoded features from the autoencoder and classifies them into categories having normal traffic and attack types including DDoS, DoS, Malware, Man-in-the-Middle, Phishing, Ransomware, and SQL Injection attacks. A preprocessing module normalizes input data and encodes categorical features including IP addresses and protocol information. An anomaly detection module identifies deviations from normal network behavior based on reconstruction error analysis between original and reconstructed data."
Disclaimer: Curated by HT Syndication.
