Steganalysis using image quality metrics

By Ismail Avcibas, Nasir D. Memon, Bülent Sankur. IEEE Transactions on Image Processing, 2003

659 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/12be7bb77aba6d621430353f2c0a784579d35d04

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Rich Models for Steganalysis of Digital Images (2012, neutral): “Personal use of this material is permitted.”
Low-Complexity Features for JPEG Steganalysis Using Undecimated DCT (2015, methodology): “Selected examples of popular feature sets proposed for detection of steganography in JPEG images are the historically first image quality metric features [1], firstorder statistics of wavelet coefficients [8], Markov features formed by sample intra-block conditional probabilities [29], inter- and in”
Deep Learning Hierarchical Representations for Image Steganalysis (2017, methodology): “idea was initially proposed in [17] and was later adopted and developed in several subsequent methods [4], [15], [16], [18].”
Feature-Based Steganalysis for JPEG Images and Its Implications for Future Design of Steganographic Schemes (2004, background): “Based on the previous work of Eggers [8], Tzschoppe [9] constructed a JPEG steganographic scheme (HPDM) that is undetectable using Farid’s scheme.”
Feature mining and pattern classification for steganalysis of LSB matching steganography in grayscale images (2008, methodology): “[17] utilized analysis of variance (ANOVA) to choose good image quality metrics.”
Image Quality Assessment for Fake Biometric Detection: Application to Iris, Fingerprint, and Face Recognition (2014, methodology): “In the present work we propose a novel parameterization using 25 general image quality measures.”
Statistically undetectable jpeg steganography: dead ends challenges, and opportunities (2007, methodology): “Based on the comparison in [29], blind steganalysis constructed using this feature vector achieves performance that is one of the best compared to currently available blind steganalysis classifiers capable of detecting stego content in JPEG images [3, 2, 33, 1, 25, 10, 39, 9, 29, 12].”
Deep Residual Network for Steganalysis of Digital Images (2019, background): “[1], [2] and Farid [18] in early 2000’s and was later greatly improved by representing images with higherorder statistics of noise residuals or DCT coefficients [43], [49], [68].”
An improved approach to steganalysis of JPEG images (2010, methodology): “utilized the analysis of variance (ANOVA) to select statistically significant features [1,11].”
Source camera identification based on CFA interpolation (2005, background): “In our prior work [1], we studied the same problem and identified a set of image features by selectively combining the features based on image quality metrics [3] and higher-order statistics of images [4].”
Digital image forensics via intrinsic fingerprints (2008, background): “Further, the estimates are shown to be robust to moderate levels of postprocessing operations, such as JPEG compression, and white balancing done inside the cameras [33].”
Merging Markov and DCT features for multi-class JPEG steganalysis (2007, neutral): “g ij(J1) − g d ij(J2), (i, j) ∈ {(2, 1), (3, 1), (4, 1), (1, 2), (2, 2), (3, 2), (1, 3), (2, 3), (1, 4)}.”
New blind steganalysis and its implications (2006, methodology): “The concept of blind steganalysis appeared for the first time in the work of Avcibas et al.(5) Farid et al.”
Benchmarking for Steganography (2008, background): “There are basically two choices: 1) analytical models, in which c is modeled as a sequence of iid random variables [28] (or Markov chains [39]) and 2) high-dimensional models based on features extracted from the cover/stego objects [32, 13, 2, 1, 43, 36, 26, 11].”
Using decision fusion of feature selection in digital forensics for camera source model identification (2012, methodology): “The statistical evidence of steganography is the major focus in [2], and we found 5 image quality features (seen in Table 3): mean square error, mean absolute error, image fidelity, normalized cross correlation, and spectral phase-magnitude error.”