# Towards Improved Steganalysis: When Cover Selection is Used in Steganography

Wang, Zichi, Li, Shujun, Zhang, Xinpeng (2019) Towards Improved Steganalysis: When Cover Selection is Used in Steganography. IEEE Access, 7 . pp. 168914-168921. ISSN 2169-3536. (doi:10.1109/ACCESS.2019.2955113) (KAR id:79178)

PDF Publisher pdf
Language: English

 Preview
Official URL
https://doi.org/10.1109/ACCESS.2019.2955113

## Abstract

This paper proposes an improved steganalytic method when cover selection is used in steganography. We observed that the covers selected by existing cover selection methods normally have different characteristics from normal ones, and propose a steganalytic method to capture such differences. As a result, the detection accuracy of steganalysis is increased. In our method, we consider a number of images collected from one or more target (suspected but not known) users, and use an unsupervised learning algorithm such as $k$ -means to adapt the performance of a pre-trained classifier towards the cover selection operation of the target user(s). The adaptation is done via pseudo-labels from the suspected images themselves, thus allowing the re-trained classifier more aligned with the cover selection operation of the target user(s). We give experimental results to show that our method can indeed help increase the detection accuracy, especially when the percentage of stego images is between 0.3 and 0.7.

Item Type: Article 10.1109/ACCESS.2019.2955113 Cover selection, steganography, steganalysis, clustering Q Science > QA Mathematics (inc Computing science) > QA 75 Electronic computers. Computer scienceQ Science > QA Mathematics (inc Computing science) > QA 76 Software, computer programming, > QA76.575 Multimedia systemsT Technology > TK Electrical engineering. Electronics. Nuclear engineering > TK5101 Telecommunications Faculties > University wide - Teaching/Research Groups > Centre for Cyber Security ResearchFaculties > Sciences > School of Computing > Security Group Shujun Li 05 Dec 2019 19:57 UTC 06 Dec 2019 12:09 UTC https://kar.kent.ac.uk/id/eprint/79178 (The current URI for this page, for reference purposes) https://orcid.org/0000-0003-0283-5338 https://orcid.org/0000-0001-5628-7328 https://orcid.org/0000-0001-5867-1315