Вісники та науково-технічні збірники, журнали

Permanent URI for this communityhttps://ena.lpnu.ua/handle/ntb/12

Browse

Subject: search.filters.subject.digital image steganalysis

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Software Implementation of Modified LSB Algorithm with Shamir`s Secret Sharing
    (Видавництво Львівської політехніки, 2022-02-28) Pavlov, M.; Yurchak, I.; Lviv Polytechnic National University
    Today, it is often necessary to transmit a confidential message of a small volume, while the use of complex cryptographic systems is difficult for some reasons. One of these reasons is the impossibility of using reliable products, which, as a rule, are commercial and unavailable to the average computer user. In modern information society, many services are provided with the help of computer networks and information technologies. Information presented in digital form must be reliably protected from many threats: unauthorized access and use, destruction, forgery, leakage, violation of license agreements, disclaimer of authorship, etc. Information protection is extremely important in both commercial and government spheres. The issues of developing effective methods of protecting digital information, in particular methods of computer steganography and steganalysis, are relevant and important for the state and society. To achieve the goal, it is necessary to propose a method of increasing stego-resistance, determine the effectiveness of the created solution and analyze the obtained results. The object of research is the process of protecting information embedded in a graphic econtainer. The subject of research is methods and algorithms of computer steganography and steganalysis for images. The research methods used in this work are based on steganographic algorithms.
  • Thumbnail Image
    Item
    Performance analysis of stego image calibration with the usage of denoising autoencoders
    (Видавництво Львівської політехніки, 2022-06-06) Progonov, Dmytro; Igor Sikorsky Kyiv Polytechnic Institute
    Methods for early detection of sensitive information leakage by data transmission in open (public) communication systems have been of special interest. Reliable detection of modified (stego) cover files, like digital images, requires usage of computation-intensive methods of statistical steganalysis, namely covering rich models and deep convolutional neural networks. Necessity of finetuning parameters of such methods to minimize detection accuracy for each embedding methods has made fast retrain of stegdetectors in real cases impossible. Therefore, development of low-complexity methods for detection of weak alterations of cover image parameters under limited prior information about used embedding methods has been required. For solving this task, we have proposed to use special architectures of artificial neural networks, such as denoising autoencoder. Ability of such networks to estimate parameters of original (cover) image from the noisy ones under limited prior information about introduced alterations has made them an attractive alternative to state-of-the-art solutions. The results of performance evaluation for shallow denoising autoencoders showed increasing of detection accuracy (up to 0.1 for Matthews correlation coefficient) in comparison with the state-of-the-art stegdetectors by preserving low-computation complexity of network retraining.