Share Email Print
cover

Proceedings Paper

A new paradigm for steganalysis via clustering
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

We propose a new paradigm for blind, universal, steganalysis in the case when multiple actors transmit multiple objects, with guilty actors including some stego objects in their transmissions. The method is based on clustering rather than classification, and it is the actors which are clustered rather than their individual transmitted objects. This removes the need for training a classifier, and the danger of training model mismatch. It effectively judges the behaviour of actors by assuming that most of them are innocent: after performing agglomerative hierarchical clustering, the guilty actor(s) are clustered separately from the innocent majority. A case study shows that this works in the case of JPEG images. Although it is less sensitive than steganalysis based on specifically-trained classifiers, it requires no training, no knowledge of the embedding algorithm, and attacks the pooled steganalysis problem.

Paper Details

Date Published: 11 February 2011
PDF: 13 pages
Proc. SPIE 7880, Media Watermarking, Security, and Forensics III, 78800U (11 February 2011); doi: 10.1117/12.872888
Show Author Affiliations
Andrew D. Ker, Oxford Univ. (United Kingdom)
Tomás Pevný, Czech Technical Univ. in Prague (Czech Republic)


Published in SPIE Proceedings Vol. 7880:
Media Watermarking, Security, and Forensics III
Nasir D. Memon; Jana Dittmann; Adnan M. Alattar; Edward J. Delp, Editor(s)

© SPIE. Terms of Use
Back to Top