Block-based image steganalysis for a multi-classifier

Cho, Seongho; Wang, Jingwei; Kuo, C.-C. Jay; Cha, Byung-Ho

doi:10.1109/icme.2010.5583564

Cited by 10 publications

(4 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both domain independent and domain related features are considered in the work where the transformation matrix is used to transfer the features from the source domain and target domain to a common feature subspace. Low ranking constrains imposed on the domain independent features help in the differentiation of stego image from the coverIn the paper, Solak et al 20 presents a performance evaluation of LSB Substitution and PVD. The parameters used in the comparison are-payload values, Peak Signal to Noise Ratio (PSNR) and Structural Similarity Index (SSIM).…”

Section: Related Workmentioning

confidence: 99%

Random embedded calibrated statistical blind steganalysis using cross validated support vector machine and support vector machine with particle swarm optimization

Shankar

Azhakath²

2023

Sci Rep

View full text Add to dashboard Cite

The evolvement in digital media and information technology over the past decades have purveyed the internet to be an effectual medium for the exchange of data and communication. With the advent of technology, the data has become susceptible to mismanagement and exploitation. This led to the emergence of Internet Security frameworks like Information hiding and detection. Examples of domains of Information hiding and detection are Steganography and steganalysis respectively. This work focus on addressing possible security breaches using Internet security framework like Information hiding and techniques to identify the presence of a breach. The work involves the use of Blind steganalysis technique with the concept of Machine Learning incorporated into it. The work is done using the Joint Photographic Expert Group (JPEG) format because of its wide use for transmission over the Internet. Stego (embedded) images are created for evaluation by randomly embedding a text message into the image. The concept of calibration is used to retrieve an estimate of the cover (clean) image for analysis. The embedding is done with four different steganographic schemes in both spatial and transform domain namely LSB Matching and LSB Replacement, Pixel Value Differencing and F5. After the embedding of data with random percentages, the first order, the second order, the extended Discrete Cosine Transform (DCT) and Markov features are extracted for steganalysis.The above features are a combination of interblock and intra block dependencies. They had been considered in this paper to eliminate the drawback of each one of them, if considered separately. Dimensionality reduction is applied to the features using Principal Component Analysis (PCA). Block based technique had been used in the images for better accuracy of results. The technique of machine learning is added by using classifiers to differentiate the stego image from a cover image. A comparative study had been during with the classifier names Support Vector Machine and its evolutionary counterpart using Particle Swarm Optimization. The idea of cross validation had also been used in this work for better accuracy of results. Further parameters used in the process are the four different types of sampling namely linear, shuffled, stratified and automatic and the six different kernels used in classification specifically dot, multi-quadratic, epanechnikov, radial and ANOVA to identify what combination would yield a better result.

show abstract

Section: Related Workmentioning

confidence: 99%

Random embedded calibrated statistical blind steganalysis using cross validated support vector machine and support vector machine with particle swarm optimization

Shankar

Azhakath²

2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…The cover image is the one that will be modified to carry the secret message, while the stego image is the output of the steganography algorithm. Traditional image steganography [1] mainly adopts the Least Significant Bits (LSB) distribution method to replace the less important pixels in the cover image to carry secret information, however, this method cannot resist steganalysis based on high-dimensional features [2, 3,4,5,6]. Then adaptive steganography algorithm [7,8,9] proposed based on the minimum distortion embedding framework, which tends to embed secret messages into textured and noisy regions, but still faces the threat of detection by deep learningbased steganalysis [10].…”

Section: Introductionmentioning

confidence: 99%

Image Steganography based on Style Transfer

Hu¹,

Ye²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Image steganography is the art and science of using images as cover for covert communications. With the development of neural networks, traditional image steganography is more likely to be detected by deep learning-based steganalysis. To improve upon this, we propose image steganography network based on style transfer, and the embedding of secret messages can be disguised as image stylization. We embed secret information while transforming the content image style. In latent space, the secret information is integrated into the latent representation of the cover image to generate the stego images, which are indistinguishable from normal stylized images. It is an end-to-end unsupervised model without pre-training. Extensive experiments on the benchmark dataset demonstrate the reliability, quality and security of stego images generated by our steganographic network.

show abstract

“…13 (Sajedi & Jamzad , 2008) Used 315 images randomly selected from Washington university image database http://www.cs.washington.edu/research/image database 14 (Joo et al , 2010) 2000 color images from the USDA NRCS Photo Gallery 15 (Lou et al , 2009) 860 color images in JPEG format from content based image Retrieval (CBIR) University of Washington, July 30 2007 http://www.cs.washington.edu/research/imagedatabase/gr oundtruth 16 (Cho et al, 2010) Among these 3580 images, 570 images were randomly downloaded from the image database 17 ) The dataset contains 1000 mono MP3 audio files with the bit rate of 128 kbps and the sample rate of 44 KHz. Each audio has the duration of 18 seconds…”

Section: (Chou Et Al 2010)mentioning

confidence: 99%

“…In (Cho et al, 2010), the authors aimed to plan one n-classifier that categorizes non-clear images based on their steganographic processes in order to distinctive cover images from stego-images. This organization is depending on steganalysis outcomes of disintegrated image chunks.…”

Section: Clustering and Other Data Mining Techniques Applied Over Thementioning

confidence: 99%