الفهرس | Only 14 pages are availabe for public view |
Abstract Nowadays, the internet can be considered the most used method to exchange information. However, the internet is a public network where the confidentiality of information can be threatened. Therefore, there was a need to protect the confidentiality of information during its transmission through the internet. In order to achieve the information security, a set of techniques have been developed such as cryptography and steganography. Steganography refers to the group of methods that can be adopted to hide the classified or confidential information within the digital media. These methods can be employed in many cases such as secure or secret communications, protecting the copyrights or authenticating the digital content, etc. Unfortunately, the steganography can be misused by malicious hackers and intruders for passing a message which can cause catastrophic situations. So, sometimes, it is necessary to detect the stego files to prevent such situations. Therefore, developing steganalysis techniques have attracted the attention of the researchers. In this thesis, we have developed a steganalysis system for detecting the LSB steganography algorithm in grey scale images. The proposed system consists of three main steps namely, feature extraction, feature reduction, classifier training. In the proposed work, we have used three supervised training algorithm. The experimental results have shown that the proposed system has a promising performance. Also, we have compared our work with other researchers’ work and the results have shown that the performance of the proposed work outperforms theirs. |