چکیده:
Information hiding and data encryption are used widely to protect data and information from anonymous access. In digital world, hiding and encrypting of the desired data into an image is a smart way to protect information with a low cost. In the digital images, steganalysis is a known method to distinguish between clean and stego images. Most of recent researches in this scope exploit feature reduction algorithms to improve the performance of correct detections. However, dimension reduction alone could not tackle the problem of steganalysis because the properties of stego images change during the steganalysis process. In this work, it is intended to propose an Image Steganalysis using visual Domain Adaptation (ISDA), which this steganalysis target images to distinguish across stego and clean images. ISDA is a dimensionality reduction approach that considers the image drifts during the steganography process in the steganalysis of target images. Moreover, ISDA employs domain invariant clustering in an embedded representation to cluster clean and stego images in the reduced subspace. The results on benchmark datasets demonstrate that ISDA thoroughly outperforms all of the state of the art methods on validation parameters, accuracy of detection and time complexity.
خلاصه ماشینی:
ISDA is a dimensionality reduction approach that considers the image drifts during the steganography process in the steganalysis of target images.
Although, significant progresses have been achieved in recent researches, the detection accuracy of current steganalysis systems based on handcrafted features is far from ideal results (Denemark et al.
In this work we propose a novel feature extraction method to steganalysis the suspicious images.
ISDA reduces joint marginal and conditional distributions across training and test sets (source and target domains, respectively) in an unsupervised manner in an embedded subspace.
ISDA shows stunning results on benchmark datasets against other available state of the art methods while standard classifiers often demonstrate poor recognitions due to significant difference across source and target domains.
(2014) proposed a novel approach to detect stego images based on bee colony feature selection method.
In this paper, we propose a joint marginal and conditional distribution adaptation method that employs domain invariant clustering to discriminate between various images.
Motivation Most of the conventional solutions for the problem of steganalysis benefit from the dimensionality reduction either feature selection or feature extraction without considering that the nature and the properties of images have been changed during the steganography process.
Conclusion In this work, a novel feature extraction method based on Visual Domain Adaptation (VDA) is proposed to extract the optimal feature subset for steganalysis.
The proposed feature extraction method based on VDA is completely effective and can be used in other domain of noisy image processing like OCR.