Ensemble Classifiers for Steganalysis of Digital Media

By Jan Kodovský, Jessica J. Fridrich, Vojtech Holub. IEEE Transactions on Information Forensics and Security, 2012

1,041 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/885af28a751553be48a25b411a5d492767d4cf65

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Yedroudj-Net: An Efficient CNN for Spatial Steganalysis (2018, positive): “0 .4 bpp) compared to SRM+EC.”
Deep residual learning for image steganalysis (2018, methodology): “Then, a binary classifier such as support vector machine [21] or ensemble classifier [15], is trained based on extracted features to discriminate cover images and stego images.”
Steganalysis of Adaptive JPEG Steganography Using 2D Gabor Filters (2015, methodology): “In addition, in literature [23, 17, 8, 13, 14], the ﬁnal detection accuracy are all obtained by ensemble classiﬁer [19] after features extraction.”
Deep Residual Network for Steganalysis of Digital Images (2019, neutral): “It culminated in what is recognized today as steganalysis with rich models [9], [15], [17], [19], [30], [38], [50], [53] and scalable machine learning [13], [40], [44].”
Embedding Watermarks into Deep Neural Networks (2017, methodology): “Steganalysis [21, 27] is a method for detecting the presence of secretly hidden data (e.”
Depth-Wise Separable Convolutions and Multi-Level Pooling for an Efficient Spatial CNN-Based Steganalysis (2020, methodology): “Our proposed CNN network is compared with five popular networks: Xu-Net [17], Ye-Net [19] (without the selectionchannel information), Yedroudj-Net [21], SRNet [39], and SRM + EC standing for the hand-crafted feature set named Spatial-Rich-Model [13] and Ensemble Classifier [32].”
Can Forensic Detectors Identify GAN Generated Images? (2018, methodology): “With the obtained features, we trained FLD (fisher linear discriminant) ensemble classifiers [20] to classify the generated images and real images.”
Steganalysis of JPEG images using rich models (2012, methodology): “We use the ensemble classiﬁer [9, 10] for all experiments as it enables fast training in high-dimensional feature spaces and its performance on low-dimensional feature sets is comparable to the much more complex SVMs [10].”
A New Payload Partition Strategy in Color Image Steganography (2020, methodology): “The ensemble classifier [38] with Fisher linear discriminant as the base learner is incorporated in our experiments, because it enables fast training in high-dimensional feature spaces and has a comparable performance to that of SVM [39] working on low-dimensional feature sets.”
Digital image steganography using universal distortion (2013, methodology): “All classifiers were implemented using the ensemble [26] with Fisher linear discriminant as the base learner.”
Universal distortion function for steganography in an arbitrary domain (2014, methodology): “The security is quantified using the ensemble’s ‘out-ofbag’ (OOB) error EOOB, which is an unbiased estimate of the minimal total testing error under equal priors, PE = minPFA (1)2 (PFA +PMD) [26].”
A new cost function for spatial image steganography (2014, methodology): “And the performances are evaluated by steganalyzers using 34,671dimensional feature set SRM [9], and 6,000-dimensional feature set MCNUQ [11], with ensemble classifiers [16].”
Selection-channel-aware rich model for Steganalysis of digital images (2014, methodology): “The detectors were trained as binary classifiers implemented using the FLD ensemble [15] with default settings.”
Low-Complexity Features for JPEG Steganalysis Using Undecimated DCT (2015, methodology): “As described in the original publication [21], the ensemble by default minimizes the total classification error probability under equal priors PE.”