MUMBAI, India, July 13 -- Intellectual Property India has published a patent application (202611053904 A) filed by Mangalayatan University, Aligarh; Mr. Arshil Noor; and Mr. Hamza Zaki on April 28, 2026, for A Secure Real-Time Examination Framework Using Chaos-Based Image Encryption And Densenet-Based Behavioral Pattern Analysis With Hybrid Human Correlation.
Inventors include Mr. Arshil Noor; Mr. Hamza Zaki; Dr. Tabrez Nafis; and Dr. Mohammad Sarfraz.
The application for the patent was published on July 10, 2026, under issue no. 28/2026.
Abstract: The present invention relates to a secure real-time examination framework system (100) for conducting and monitoring online or remote examinations. The system (100) comprises a student examination interface module (1) for capturing live image frames or video frames of a candidate, a chaos-based image encryption module (2) for encrypting the captured frames before transmission, and a secure communication module (3) for transmitting encrypted frames to a central examination server. A decryption and preprocessing module (4) decrypts and preprocesses the received frames, and a DenseNet-based behavioural analysis module (5) analyses candidate behaviour. A behavioural feature extraction module (6) extracts behavioural indicators including eye movement, head pose, facial expression, object presence, background condition, body movement, and face count information. A real-time anomaly detection module (7) generates anomaly alerts based on AI analysis and behavioural features. A monitoring dashboard module (8) displays real- time alerts to invigilators and a central monitoring authority. A hybrid human correlation module (9) validates AI-generated alerts using human inputs, and a decision recording module (10) stores secured audit records. The invention improves examination data confidentiality, behavioural authenticity, anomaly detection accuracy, and human-validated examination integrity.
Disclaimer: Curated by HT Syndication.
