Share Email Print
cover

Proceedings Paper

Multi-class blind steganalysis for JPEG images
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In this paper, we construct blind steganalyzers for JPEG images capable of assigning stego images to known steganographic programs. Each JPEG image is characterized using 23 calibrated features calculated from the luminance component of the JPEG file. Most of these features are calculated directly from the quantized DCT coefficients as their first order and higher-order statistics. The features for cover images and stego images embedded with three different relative message lengths are then used for supervised training. We use a support vector machine (SVM) with Gaussian kernel to construct a set of binary classifiers. The binary classifiers are then joined into a multi-class SVM using the Max-Win algorithm. We report results for six popular JPEG steganographic schemes (F5, OutGuess, Model based steganography, Model based steganography with deblocking, JP Hide and Seek, and Steghide). Although the main bulk of results is for single compressed stego images, we also report some preliminary results for double-compressed images created using F5 and OutGuess. This paper demonstrates that it is possible to reliably classify stego images to their embedding techniques. Moreover, this approach shows promising results for tackling the diffcult case of double compressed images.

Paper Details

Date Published: 16 February 2006
PDF: 13 pages
Proc. SPIE 6072, Security, Steganography, and Watermarking of Multimedia Contents VIII, 60720O (16 February 2006); doi: 10.1117/12.640943
Show Author Affiliations
Tomáš Pevný, SUNY Binghamton (United States)
Jessica Fridrich, SUNY Binghamton (United States)


Published in SPIE Proceedings Vol. 6072:
Security, Steganography, and Watermarking of Multimedia Contents VIII
Edward J. Delp III; Ping Wah Wong, Editor(s)

© SPIE. Terms of Use
Back to Top