Quantitative and Binary Steganalysis in JPEG: A Comparative Study (original) (raw)
Related papers
JPEG Steganalysis Using HBCL Statistics and FR Index
Intelligence and Security Informatics, 2010
Blind Steganalysis attempts to detect steganographic data without prior knowledge of either the embedding algorithm or the 'cover' image. This paper proposes new features for JPEG blind steganalysis using a combination of Huffman Bit Code Length (HBCL) Statistics and File size to Resolution ratio (FR Index); the Huffman Bit File Index Resolution (HUBFIRE) algorithm proposed uses these functionals to build the classifier using a multi-class Support Vector Machine (SVM). JPEG images spanning a wide range of resolutions are used to create a 'stego-image' database employing three embedding schemes-the advanced Least Significant Bit encoding technique, that embeds in the spatial domain, a transform-domain embedding scheme: JPEG Hide-and-Seek and Model Based Steganography which employs an adaptive embedding technique. This work employs a multi-class SVM over the proposed 'HUBFIRE' algorithm for statistical steganalysis, which is not yet explored by steganalysts. Experiments conducted prove the model's accuracy over a wide range of payloads and embedding schemes.
In this paper, we introduce a new feature-based steganalytic method for JPEG images and use it as a benchmark for comparing JPEG steganographic algorithms and evaluating their embedding mechanisms. The detection method is a linear classifier trained on feature vectors corresponding to cover and stego images. In contrast to previous blind approaches, the features are calculated as an L 1 norm of the difference between a specific macroscopic functional calculated from the stego image and the same functional obtained from a decompressed, cropped, and recompressed stego image. The functionals are built from marginal and joint statistics of DCT coefficients. Because the features are calculated directly from DCT coefficients, conclusions can be drawn about the impact of embedding modifications on detectability. Three different steganographic paradigms are tested and compared. Experimental results reveal new facts about current steganographic methods for JPEGs and new design principles for more secure JPEG steganography. system is considered broken. For a more exact treatment of the concept of steganographic security, the reader is referred to [1,2].
RTCSP ’ 10 1 Feature Based Classification System for Jpeg Steganalysis
2010
The objective of steganalysis is to detect messages hidden in cover images, such as digital images. The ultimate goal of a steganalyst is to extract and decipher the secret message. In this paper, we present a powerful new blind steganalytic scheme that can reliably detect hidden data in JPEG images. This would increase the success rate of steganalysis by detecting data in transform as well as spatial domain. This scheme is feature based in the sense that features that are sensitive to embedding changes and being employed as means of steganalysis. The features are extracted in DCT domain. DCT domain features have extended DCT features and Markovian features merged together to eliminate the drawbacks of both. The blind steganalytic technique has a broad spectrum of analyzing different embedding techniques. The feature based steganalytic technique is used in the DCT domain to extract about 23 functionals and classify the dataset according to these functionals. The feature set can be i...
Neighboring joint density-based JPEG steganalysis
ACM Transactions on Intelligent Systems and Technology, 2011
The threat posed by hackers, spies, terrorists, and criminals, etc. using steganography for stealthy communications and other illegal purposes is a serious concern of cyber security. Several steganographic systems that have been developed and made readily available utilize JPEG images as carriers. Due to the popularity of JPEG images on the Internet, effective steganalysis techniques are called for to counter the threat of JPEG steganography. In this article, we propose a new approach based on feature mining on the discrete cosine transform (DCT) domain and machine learning for steganalysis of JPEG images. First, neighboring joint density features on both intra-block and inter-block are extracted from the DCT coefficient array and the absolute array, respectively; then a support vector machine (SVM) is applied to the features for detection. An evolving neural-fuzzy inference system is employed to predict the hiding amount in JPEG steganograms. We also adopt a feature selection method of support vector machine recursive feature elimination to reduce the number of features. Experimental results show that, in detecting several JPEG-based steganographic systems, our method prominently outperforms the well-known Markov-process based approach.
Performance Evaluation of Different Universal Steganalysis Techniques in JPG Files
Annales UMCS, Informatica, 2012
Steganalysis is the art of detecting the presence of hidden data in files. In the last few years, there have been a lot of methods provided for steganalysis. Each method gives a good result depending on the hiding method. This paper aims at the evaluation of five universal steganalysis techniques which are "Wavelet based steganalysis", "Feature Based Steganalysis", "Moments of characteristic function using wavelet decomposition based steganalysis", "Empirical Transition Matrix in DCT Domain based steganalysis", and "Statistical Moment using jpeg2D array and 2D characteristic function". A large Dataset of Images-1000 images-are subjected to three types of steganographic techniques which are "Outguess", "F5" and "Model Based" with the embedding rate of 0.05, 0.1, and 0.2. It was followed by extracting the steganalysis feature used by each steganalysis technique for the stego images as well as the cover image. Then half of the images are devoted to train the classifier. The Support vector machine with a linear kernel is used in this study. The trained classifier is then used to test the other half of images, and the reading is reported The "Empirical Transition Matrix in DCT Domain based steganalysis" achieves the highest values among all the properties measured and it becomes the first choice for the universal steganalysis technique. Pobrane z czasopisma Annales AI-Informatica http://ai.annales.umcs.pl
Steganalysis of JPEG Images with Joint Transform Features
Lecture Notes in Computer Science, 2009
In this paper, a universal steganalysis scheme for JPEG images based upon joint transform features is presented. We first analyzed two different transform domains (Discrete Cosine Transform and Discrete Wavelet Transform) separately, to extract features for steganalysis. Then a combination of these two feature sets is constructed and employed for steganalysis. A Fisher Linear Discriminant classifier is trained on features from both clean and steganographic images using all three feature sets and subsequently used for classification. Experiments performed on images embedded with two variants of F5 and Model based steganographic techniques reveal the effectiveness of proposed steganalysis approach by demonstrating improved detection for joint features.
Comparing Classifiers for Universal Steganalysis
2020
Universal Steganalysis rely on extracting higher order statistical features that gets disturbed when hiding the message in a clean image. Due to content adaptive steganographies like HUGO, WOW etc. which embed the data more in textured areas of the image rather than smooth areas by minimizing the distortion of the image itself, first order features are not sufficient to differentiate clean and stego images. Thus, rich models come into picture in which a large number of features are extracted based on higher order noise residuals of clean and stego images. Thus, Universal Steganalyser is essentially a supervised classifier built on high dimensional feature set. To work with such high dimensional features on a large dataset of images is a very challenging task due to curse of dimensionality as well as computationally very expensive. This paper aims at comparing performance of three techniques-Ensemble classifier, Logistic regression and K-Nearest Neighbors on Spatial Rich Model features extracted for benchmarked dataset BOSSbase_1.01, for the better discrimination of clean and stego images.
An analysis of quality factor on image steganalysis
2010
Internet has emerged as a popular medium of communication, not only for common people but also for criminals. Various modes of covert communication are adopted by such elements. Steganography hides the information in digital images without changing their visual perception. These images can then be transferred over internet, without causing any suspicion to an observer. Steganalysis techniques inspect the images and detect the presence of hidden messages. In this paper, we have investigated the effect of quality factor of JPEG images on steganalysis using Discrete Cosine Transform. Features are extracted in Discrete Cosine Transform domain using higher order statistics, and subsequently a Fisher Linear Discriminant classifier is trained using different clean and steganographic images at different JPEG compression ratios i.e., quality factor. The quantitative results of experiments demonstrate that a classifier trained on particular quality factor gives better detection accuracy for images compressed with the same or a lower quality factor, but gives degraded performance of detection for images compressed with higher quality factor. This inference can aid in developing improved quality independent steganalysis mechanisms.
Pooled Steganalysis in JPEG: how to deal with the spreading strategy?
2019 IEEE International Workshop on Information Forensics and Security (WIFS), 2019
In image pooled steganalysis, a steganalyst, Eve, aims to detect if a set of images sent by a steganographer, Alice, to a receiver, Bob, contains a hidden message. We can reasonably assess that the steganalyst does not know the strategy used to spread the payload across images. To the best of our knowledge, in this case, the most appropriate solution for pooled steganalysis is to use a Single-Image Detector (SID) to estimate/quantify if an image is cover or stego, and to average the scores obtained on the set of images. In such a scenario, where Eve does not know the spreading strategies, we experimentally show that if Eve can discriminate among few well-known spreading strategies, she can improve her steganalysis performances compared to a simple averaging or maximum pooled approach. Our discriminative approach allows obtaining steganalysis efficiencies comparable to those obtained by a clairvoyant, Eve, who knows the Alice spreading strategy. Another interesting observation is that DeLS spreading strategy behaves really better than all the other spreading strategies. Those observations results in the experimentation with six different spreading strategies made on Jpeg images with J-UNIWARD, a state-of-the-art Single-Image-Detector, and a discriminative architecture that is invariant to the individual payload in each image, invariant to the size of the analyzed set of images, and build on a binary detector (for the pooling) that is able to deal with various spreading strategies.