Advances In Cyber-Physical Systems. – 2022. – Vol. 7, No. 1

Permanent URI for this collectionhttps://ena.lpnu.ua/handle/ntb/57965

Науковий журнал

Засновник і видавець Національний університет «Львівська політехніка». Виходить двічі на рік з 2016 року.

Advances in Cyber-Physical Systems / Lviv Polytechnic National University ; editor-in-chief A. Melnyk. – Lviv : Lviv Politechnic Publishing House, 2022. – Volume 7, number 1. – 64 p. : il.

Зміст


1
8
15
22
29
38
46
55

Content (Vol. 7, No 1)


1
8
15
22
29
38
46
55

Browse

Filters

20221

Settings

Has files: YesSubject: search.filters.subject.adaptive embedding methods

Search Results

Now showing 1 - 1 of 1
  • 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.