Data-hiding using steganography algorithm becomes an important technique to prevent unauthorized users to have access to a secret data. In this paper, steganography algorithm has been constructed to hide a secret data in a gray and a color images, this algorithm is named deep hiding/extraction algorithm (DHEA) to modify multi-level steganography (MLS). The suggested hiding algorithm is based on modified least significant bit (MDLSB) to scatter data in a cover-image and it utilizes a number of levels; where each level perform hiding data on a gray image except the last level that applies a color image to keep secret data. Furthermore, proper randomization approach with two layers is implemented; the first layer uses random pixels selection for hiding a secret data at each level, while the second layer implements at the last level to move randomly from segment to the others. In addition, the proposed hiding algorithm implements an effective lossless image compression using DEFLATE algorithm to make it possible to hide data into a next level. Dynamic encryption algorithm based on Advanced Encryption Standard (AES) is applied at each level by changing cipher keys (Ck) from level to the next, this approach has been applied to increase the security and working against attackers. Soft computing using a meta-heuristic approach based on artificial bee colony (ABC) algorithm has been introduced to achieve smoothing on pixels of stego-image, this approach is effective to reduce the noise caused by a hidden large amount of data and to increase a stego-image quality on the last level. The experimental result demonstrates the effectiveness of the proposed algorithm with bee colony DHA-ABC to show high-performing to hide a large amount of data up to four bits per pixel (bpp) with high security in terms of hard extraction of a secret message and noise reduction of the stego-image. Moreover, using deep hiding with unlimited levels is promising to confuse attackers and to compress a deep sequence of images into one image.
This study deals with constructing and implementing new algorithm based on hiding a large amount of data (image, audio, text) file into color BMP image. We have been used adaptive image filtering and adaptive image segmentation with bits replacement on the appropriate pixels. These pixels are selected randomly rather than sequentially by using new concept defined by main cases with their sub cases for each byte in one pixel. This concept based on both visual and statistical. According to the steps of design, we have been concluded 16 main cases with their sub cases that cover all aspects of the input data into color bitmap image. High security layers have been proposed through three layers to make it difficult to break through the encryption of the input data and confuse steganalysis too. Our results against statistical and visual attacks are discussed and make comparison with the previous Steganography algorithms like S-Tools. We show that our algorithm can embed efficiently a large amount of data that has been reached to 75% of the image size with high quality of the output.
A method based on neural network with Back-Propagation Algorithm (BPA) and Adaptive Smoothing Errors (ASE), and a Genetic Algorithm (GA) employing a new concept named Adaptive Relaxation (GAAR) is presented in this paper to construct learning system that can find an Adaptive Mesh points (AM) in fluid problems. AM based on reallocation scheme is implemented on different types of two steps channels by using a three layer neural network with GA. Results of numerical experiments using Finite Element Method (FEM) are discussed. Such discussion is intended to validate the process and to demonstrate the performance of the proposed learning system on three types of two steps channels. It appears that training is fast enough and accurate due to the optimal values of weights by using a few numbers of patterns. Results confirm that the presented neural network with the proposed GA consistently finds better solutions than the conventional neural network.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.