Hossain, Muhammad IqbalHossain, Md. IrtizaKadir, SamiulFagun, Farhan IshraqSamiul, IshtiaqSaukhin, Rafi Zaman2024-10-302024-10-30©20242024-05ID 20101481ID 20101211ID 20101295ID 20101133ID 20301143http://hdl.handle.net/10361/24471Cataloged from PDF version of thesis.Includes bibliographical references (pages 50-51).This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2024.In today’s world of information and communication tools, data security is critical for information diffusion. With the growth of extensive multimedia sharing and secret discussions, data concealment has become increasingly vital. Steganography encompasses various types, including image steganography, audio steganography, video steganography, text steganography, network steganography, and digital watermarking. Traditionally, image steganography involves concealing an image within the least significant pixels of a cover image. However, recent advancements have leveraged neural networks to encode and decode secret images within cover images. Our objective is to utilize neural networks especially convolutional neural network to hide multiple images within a single cover image while maximizing payload capacity and minimizing errors in the encoding and decoding processes.51 pagesenBrac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission.SteganographyImage steganographyNeural networkConvolutional neural networkNeural networks (Computer science).Data encryption (Computer science).Image processing.Computational intelligence.Thesis