MUMBAI, India, June 22 -- Intellectual Property India has published a patent application (202621048974 A) filed by Moresh Madhukar Mukhedkar; Srushti Keskar; Sairaj Patil; Suhani Patil; Sanyukta Korade; Prof. Anurag Kumar; Dr. Vivek Patil; and Dr. Shweta Koparde on April 17, 2026, for Ai-Driven Deep Learning Based Secure Image Steganography.

Inventors include Moresh Madhukar Mukhedkar; Srushti Keskar; Sairaj Patil; Suhani Patil; Sanyukta Korade; Prof. Anurag Kumar; Dr. Vivek Patil; and Dr. Shweta Koparde.

The application for the patent was published on June 12, 2026, under issue no. 24/2026.

Abstract: With the rapid growth of digital communication, ensuring secure transmission of sensitive information has become a critical challenge. This project presents an advanced approach to secure data hiding using Image Steganography combined with Deep Learning techniques. The proposed system embeds secret messages within digital images in a way that is imperceptible to human vision. A deep learning-based model, such as an autoencoder with Convolutional Neural Networks, is used to perform encoding and decoding operations. The encoder network hides the secret data inside a cover image to generate a stego image, while the decoder network extracts the hidden information accurately. The system is designed to maintain high image quality while ensuring strong security against steganalysis attacks. Performance is evaluated using metrics such as PSNR, SSIM, and Bit Error Rate (BER), demonstrating improved efficiency and robustness compared to traditional methods. Additionally, a user-friendly interface is developed to allow users to easily upload images, input secret messages, and perform encoding and decoding operations. The trained model is deployed using modern web frameworks, enabling real-time and scalable applications. Overall, the proposed system provides a secure, efficient, and intelligent solution for confidential data transmission in various domains such as military communication, digital watermarking, and data protection.

Disclaimer: Curated by HT Syndication.