New approach to steganography detection via steganalysis framework

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F17%3A10236988" target="_blank" >RIV/61989100:27240/17:10236988 - isvavai.cz</a>

Výsledek na webu

<a href="http://iiti-conf.org/" target="_blank" >http://iiti-conf.org/</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-319-68321-8_51" target="_blank" >10.1007/978-3-319-68321-8_51</a>

Jazyk výsledku

angličtina

Název v původním jazyce

New approach to steganography detection via steganalysis framework

Popis výsledku v původním jazyce

The aim is to propose basic steganalytical tool that can use multiple methods of analysis. We describe two detection methods that were imple-mented. These methods include improved detection capability than convention-al steganalytical tools thanks to use of artificial neural network and several oth-er innovative improvements. In our work is important to understand the beha-vior of the targeted steganography algorithm. Then we can use its weaknesses to increase the detection capability. We analyze prepared stegogrammes by ap-plication of several conventional algorithms such as image difference. Then we can determine where are the most suitable areas of image for embedding the message by steganography algorithm. Two of our plug-ins are focused on steganography algorithms Steghide, OutGuess2.0 and F5. These algorithms are open source and easy accessible, so the risk of their abuse is high. We use several approaches, such as calibration process and blockiness calculation to detect the presence of steganography mes-sage in suspected image. Calibration process is designed for creation of calibra-tion image, that represents the original cover work and for comparison to sus-pected image. Blockiness calculation serves us as a statistical metric that react to the presence of secret message. Next we deploy the artificial neural network to improve detection capability. Second plug-in utilizes a detection method that is based on analysis of inner structures of JPEG format. This detection method uses overall quality calcula-tion based on quantization tables and Huffman coding table. These informations are processed by neural network that is able to decide whatever the suspicious file contains embedded data and which steganography algorithm was used to create this file with tested confidence larger than 93% and for detection capabil-ity up to 99%.

Název v anglickém jazyce

New approach to steganography detection via steganalysis framework

Popis výsledku anglicky

The aim is to propose basic steganalytical tool that can use multiple methods of analysis. We describe two detection methods that were imple-mented. These methods include improved detection capability than convention-al steganalytical tools thanks to use of artificial neural network and several oth-er innovative improvements. In our work is important to understand the beha-vior of the targeted steganography algorithm. Then we can use its weaknesses to increase the detection capability. We analyze prepared stegogrammes by ap-plication of several conventional algorithms such as image difference. Then we can determine where are the most suitable areas of image for embedding the message by steganography algorithm. Two of our plug-ins are focused on steganography algorithms Steghide, OutGuess2.0 and F5. These algorithms are open source and easy accessible, so the risk of their abuse is high. We use several approaches, such as calibration process and blockiness calculation to detect the presence of steganography mes-sage in suspected image. Calibration process is designed for creation of calibra-tion image, that represents the original cover work and for comparison to sus-pected image. Blockiness calculation serves us as a statistical metric that react to the presence of secret message. Next we deploy the artificial neural network to improve detection capability. Second plug-in utilizes a detection method that is based on analysis of inner structures of JPEG format. This detection method uses overall quality calcula-tion based on quantization tables and Huffman coding table. These informations are processed by neural network that is able to decide whatever the suspicious file contains embedded data and which steganography algorithm was used to create this file with tested confidence larger than 93% and for detection capabil-ity up to 99%.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20202 - Communication engineering and systems

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2017

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Advances in Intelligent Systems and Computing. Volume 679

ISBN

978-3-319-68320-1

ISSN

2194-5357

e-ISSN

2194-5365

Počet stran výsledku

8

Strana od-do

1-8

Název nakladatele

Springer

Místo vydání

Cham

Místo konání akce

Varna

Datum konání akce

14. 9. 2017

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—