Digital Library

cab1

 
Title:      A NOVEL APPROACH FOR SECURE STEGANOGRAPHY: INTER-FORMAT CONVERSION COMPENSATION FOR ENHANCED DATA SECURITY
Author(s):      Hasan Azooz, Khawla Ben Salah, Monji Kherallah and Mohamed Saber Naceur
ISBN:      978-989-8704-53-5
Editors:      Paula Miranda and Pedro IsaĆ­as
Year:      2023
Edition:      Single
Keywords:      Steganography, JPEG Images, Embedding Information
Type:      Full
First Page:      85
Last Page:      93
Language:      English
Cover:      cover          
Full Contents:      click to dowload Download
Paper Abstract:      Steganography research and development are becoming more common in the information society, due to the widespread use of digital media formats and the challenges of managing digital resources and controlling the ownership and use of computer files. At thesame time, addressing steganography challenges is an important issue in the context of the evolving network communication infrastructure for Internet users - participants in open and uncontrolled interaction in the media space. The research concludes that it is necessaryto develop a newqualitative concealing algorithmthat enables the hiding of large data. Amounts of data (MB) in still images in commongraphic formats The JPEG format was chosen as the most popular in everyday use scenarios for digital graphics, especially digital images.A qualitative analysis of classes of steganography algorithms focused on embedding data in graphic images for the purpose of covertly transmitting large amounts of data in digital images in JPEG format was carried out, resulting in the development of algorithms for working with digital image structures in JPEG and BMP graphic formats. A mechanism has been developed to compensate for the loss of data bits during inter-format conversions. Additionally, programmatic functions have been established for data insertion and extraction. Machine learning can be used to fine-tune the embedding process, making the resulting stego images harder to decipher for attackers. By usinga machine learning model that has been trained to distinguish between cover and stego images, the embedding process can be fine-tuned tomake the stego image less distinguishable fromthe original cover image.
   

Social Media Links

Search

Login