A mishmash of methods for mitigating the model mismatch mess

Andrew D. Ker; Tomáš Pevný

doi:10.1117/12.2038908

19 February 2014 A mishmash of methods for mitigating the model mismatch mess

Andrew D. Ker, Tomáš Pevný

Proceedings Volume 9028, Media Watermarking, Security, and Forensics 2014; 90280I (2014) https://doi.org/10.1117/12.2038908
Event: IS&T/SPIE Electronic Imaging, 2014, San Francisco, California, United States

Abstract

The model mismatch problem occurs in steganalysis when a binary classifier is trained on objects from one cover source and tested on another: an example of domain adaptation. It is highly realistic because a steganalyst would rarely have access to much or any training data from their opponent, and its consequences can be devastating to classifier accuracy. This paper presents an in-depth study of one particular instance of model mismatch, in a set of images from Flickr using one fixed steganography and steganalysis method, attempting to separate different effects of mismatch in feature space and find methods of mitigation where possible. We also propose new benchmarks for accuracy, which are more appropriate than mean error rates when there are multiple actors and multiple images, and consider the case of 3-valued detectors which also output `don't know'. This pilot study demonstrates that some simple feature-centering and ensemble methods can reduce the mismatch penalty considerably, but not completely remove it.

Citation Download Citation

Andrew D. Ker and Tomáš Pevný "A mishmash of methods for mitigating the model mismatch mess", Proc. SPIE 9028, Media Watermarking, Security, and Forensics 2014, 90280I (19 February 2014); https://doi.org/10.1117/12.2038908

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available