Tez No	İndirme	Tez Künye	Durumu
402009		Moving from image steganalysis to motion vector based video steganalysis / Yazar:KASIM TAŞDEMİR Danışman: DR. FATİH KURUGÖLLÜ Yer Bilgisi: Queen's University Belfast / Yurtdışı Enstitü Konu:Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontrol = Computer Engineering and Computer Science and Control ; Elektrik ve Elektronik Mühendisliği = Electrical and Electronics Engineering Dizin:	Onaylandı Doktora İngilizce 2015 152 s.
Steganography is the art of covert communication. The primary purpose of it is to hide the existence of the secret message in an innocuous looking object. Steganalysis, the adversary of steganography, is the effort to detect the existence of the secret messages. As the security concerns increase of late, this research field drives more attention than before. This thesis proposes three novel solutions to the problem of the detection of the existence of secret messages embedded in motion vectors (MV) of a video. To this end, behaviours of MVs of natural videos are thoroughly examined in the beginning of the thesis. It has been demonstrated that MVs have strong spatial and temporal correlation and the correlation strength is measured for the first time. Then, the following algorithms are developed considering this fact. Firstly, a novel flatness measure for video steganalysis targeting LSB based motion vector steganography is introduced. Thus, a cover model that does not require a training based machine learning system is proposed. Secondly, a spatio-temporal rich model of motion vector planes as a part of a full steganalytic system against motion vector based steganography is proposed. Rich models, which have been used in image steganalysis, is extended to motion vector based steganalysis. Also a novel transformation so as to extend the feature set with temporal residuals is introduced. Lastly, a rich model based universal motion vector steganalysis is presented. The improvement in detection accuracy lies in several novel approaches introduced in this thesis: Firstly, temporal motion vector dependency is utilized along side the spatial dependency. Secondly, unlike the ones previously used, a diverse set of many filters which can capture aberrations introduced by various motion vector steganography methods is employed. The variety and also the number of the fil-ter kernels are substantially more than that of previous ones. Also filters up to fifth order are employed whereas at most second order filters are used by previous methods. As a result of these novelties, the proposed system can capture various de-correlations in a wide spatio-temporal range and provide a better cover model. To the knowledge of the author, the experiments section has the most comprehen-sive tests in motion vector field including 5 stego and 7 steganalysis methods. The data set used is the largest one among the sets used in previous papers including 700000 frames of video.