MUMBAI, India, Sept. 28 -- Intellectual Property India has published a patent application (202641113772 A) filed by Sreyas Institute Of Engineering And Technology on September 23, 2026, for Machine Learning-Based Fake Profile Identification System Using Support Vector Machine And Logistic Regression Models.
Inventors include Dr. Ch Janakamma; P. Archana; and P. Venkataiah.
The application for the patent was published on September 25, 2026, under issue no. 39/2026.
Abstract: The present invention discloses a machine learning-based system for automatic identification of fake profiles in social networks. The system comprises a dataset collection unit (110), pre-processing unit (120), feature extraction unit (130), and machine learning unit (140) that employs Support Vector Machine (SVM) and Logistic Regression algorithms. The system analyzes profile attributes such as username, follower count, posts, and comments to classify profiles as genuine or fake. The confusion matrix-based evaluation ensures high accuracy (up to 97.4%). This invention effectively improves detection precision, reduces manual intervention, and enhances online security.
Disclaimer: Curated by HT Syndication.
