This paper is focused on proposal of image steganographic method that is able to embedding of encoded secret message using Quick Response Code (QR) code into image data. Discrete Wavelet Transformation (DWT) domain is used for the embedding of QR code, while embedding process is additionally protected by Advanced Encryption Standard (AES) cipher algorithm. In addition, typical characteristics of QR code was broken using the encryption, therefore it makes the method more secure. The aim of this paper is design of image steganographic method with high secure level and high non-perceptibility level. The relation between security and capacity of the method was improved by special compression of QR code before the embedding process. Efficiency of the proposed method was measured by Peak Signal-to-Noise Ratio (PSNR) and achieved results were compared with other steganographic tools.

No abstract

No abstract

In this paper, proposed steganalytic method utilized for the detection of secret message is based on extraction of statistical features from cover and stego images in JPEG file format together with calibration technique. The steganalyzer concept uses Support Vector Machines (SVM) classification or Bayes classifier for training a model that is later used by the same steganalyzer in order to identify between a clean (cover) and stego image. The aim of the paper was to compare detection accuracy (ACR) of the trained models for two types of classifiers: Support Vector Machines and Bayes classifier. In this paper, five models created between cover and stego images (images obtained by nsF5, Model Based 1, Model Based 2, Modulo Histogram Fitting with Dead Zone and Pertubed Quantization steganographic method) was tested.

No abstract