TY - GEN
T1 - Quantitative steganalysis using rich models
AU - Kodovský, Jan
AU - Fridrich, Jessica
PY - 2013
Y1 - 2013
N2 - In this paper, we propose a regression framework for steganalysis of digital images that utilizes the recently proposed rich models - high-dimensional statistical image descriptors that have been shown to substantially improve classical (binary) steganalysis. Our proposed system is based on gradient boosting and utilizes a steganalysis-specific variant of regression trees as base learners. The conducted experiments confirm that the proposed system outperforms prior quantitative steganalysis (both structural and feature-based) across a wide range of steganographic schemes: HUGO, LSB replacement, nsF5, BCHopt, and MME3.
AB - In this paper, we propose a regression framework for steganalysis of digital images that utilizes the recently proposed rich models - high-dimensional statistical image descriptors that have been shown to substantially improve classical (binary) steganalysis. Our proposed system is based on gradient boosting and utilizes a steganalysis-specific variant of regression trees as base learners. The conducted experiments confirm that the proposed system outperforms prior quantitative steganalysis (both structural and feature-based) across a wide range of steganographic schemes: HUGO, LSB replacement, nsF5, BCHopt, and MME3.
UR - https://www.scopus.com/pages/publications/84878430667
U2 - 10.1117/12.2001563
DO - 10.1117/12.2001563
M3 - Conference contribution
SN - 9780819494382
T3 - Proceedings of SPIE - The International Society for Optical Engineering
BT - Proceedings of SPIE-IS and T Electronic Imaging - Media Watermarking, Security, and Forensics 2013
T2 - 2013 Media Watermarking, Security, and Forensics Conference
Y2 - 5 February 2013 through 7 February 2013
ER -