EURASIP Journal on Applied Signal Processing 
Volume 2005 (2005), Issue 17, Pages 2749-2757
doi:10.1155/ASP.2005.2749

Image Steganalysis with Binary Similarity Measures

İsmail Avcıbaş,1 Mehdi Kharrazi,2 Nasir Memon,3 and Bülent Sankur4

 1Department of Electronics Engineering, Uludağ University, Bursa 16059, Turkey
2Department of Electrical and Computer Engineering, Polytechnic University, Brooklyn 11201, NY, USA
3Department of Computer and Information Science, Polytechnic University, Brooklyn 11201, NY, USA
4Department of Electrical and Electronics Engineering, Boğaziçi University, İstanbul 34342, Turkey
Received 14 March 2004; Revised 10 May 2005

Recommended by Mauro Barni

Abstract

We present a novel technique for steganalysis of images that have been subjected to embedding by steganographic algorithms. The seventh and eighth bit planes in an image are used for the computation of several binary similarity measures. The basic idea is that the correlation between the bit planes as well as the binary texture characteristics within the bit planes will differ between a stego image and a cover image. These telltale marks are used to construct a classifier that can distinguish between stego and cover images. We also provide experimental results using some of the latest steganographic algorithms. The proposed scheme is found to have complementary performance vis-à-vis Farid's scheme in that they outperform each other in alternate embedding techniques.