CNN Steganalyzers Leverage Local Embedding Artifacts
Authors:
- 7 December 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Abstract
While convolutional neural networks have firmly established themselves as the superior steganography detectors, little human-interpretable feedback to the steganographer as to how the network reaches its decision has so far been obtained from trained models. The folklore has it that, unlike rich models, which rely on global statistics, CNNs can leverage spatially localized signals. In this paper, we adapt existing attribution tools, such as Integrated Gradients and Last Activation Maps, to show that CNNs can indeed find overwhelming evidence for steganography from a few highly localized embedding artifacts. We look at the nature of these artifacts via case studies of both modern content-adaptive and older steganographic algorithms. The main culprit is linked to “content creating changes” when the magnitude of a DCT coefficient is increased (Jsteg, –F5), which can be especially detectable for high frequency DCT modes that were originally zeros (J-MiPOD). In contrast, J-UNIWARD introduces the smallest number of locally detectable embedding artifacts among all tested algorithms. Moreover, we find examples of inhibition that facilitate distinguishing between the selection channels of stego algorithms in a multi-class detector. The authors believe that identifying and characterizing local embedding artifacts provides useful feedback for future design of steganographic schemes.Keywords
Funding Information
- NSF (2028119)
This publication has 14 references indexed in Scilit:
- Steganography by Minimizing Statistical Detectability: The cases of JPEG and Color Images2020
- Visualizing the Impact of Feature Attribution BaselinesDistill, 2020
- Deep Residual Network for Steganalysis of Digital ImagesIEEE Transactions on Information Forensics and Security, 2018
- Modeling and Extending the Ensemble Classifier for Steganalysis of Digital Images Using Hypothesis Testing TheoryIEEE Transactions on Information Forensics and Security, 2015
- Low-Complexity Features for JPEG Steganalysis Using Undecimated DCTIEEE Transactions on Information Forensics and Security, 2014
- Ensemble Classifiers for Steganalysis of Digital MediaIEEE Transactions on Information Forensics and Security, 2011
- ImageNet: A large-scale hierarchical image database2009
- Novelty detection in blind steganalysis2008
- Statistically undetectable jpeg steganography2007
- Paths and consistency in additive cost sharingInternational Journal of Game Theory, 2004