Siwei Lyu

Detecting Hidden Messages Using Higher-Order Statistics and Support Vector Machines

Techniques for information hiding have become increasingly more sophisticated and widespread. With high-resolution digital images as carriers, detecting hidden messages has become considerably more difficult. This paper describes an approach to detecting hidden messages in images that uses a wavelet-like decomposition to build higher-order statistical models of natural images. Support vector machines are then used to discriminate between untouched and adulterated images.

Steganalysis using higher-order image statistics

Techniques for information hiding (steganography) are becoming increasingly more sophisticated and widespread. With high-resolution digital images as carriers, detecting hidden messages is also becoming considerably more difficult. We describe a universal approach to steganalysis for detecting the presence of hidden messages embedded within digital images. We show that, within multiscale, multiorientation image decompositions (e.g., wavelets), first- and higher-order magnitude and phase statistics are relatively consistent across a broad range of images, but are disturbed by the presence of embedded hidden messages. We show the efficacy of our approach on a large collection of images, and on eight different steganographic embedding algorithms.

Region Duplication Detection Using Image Feature Matching

Region duplication is a simple and effective operation to create digital image forgeries, where a continuous portion of pixels in an image, after possible geometrical and illumination adjustments, are copied and pasted to a different location in the same image. Most existing region duplication detection methods are based on directly matching blocks of image pixels or transform coefficients, and are not effective when the duplicated regions have geometrical or illumination distortions. In this work, we describe a new region duplication detection method that is robust to distortions of the duplicated regions. Our method starts by estimating the transform between matched scale invariant feature transform (SIFT) keypoints, which are insensitive to geometrical and illumination distortions, and then finds all pixels within the duplicated regions after discounting the estimated transforms. The proposed method shows effective detection on an automatically synthesized forgery image database with duplicated and distorted regions. We further demonstrate its practical performance with several challenging forgery images created with state-of-the-art tools.

Higher-order Wavelet Statistics and their Application to Digital Forensics

We describe a statistical model for natural images that is built upon a multi-scale wavelet decomposition. The model consists of first- and higher-order statistics that capture certain statistical regularities of natural images. We show how this model can be useful in several digital forensic applications, specifically in detecting various types of digital tampering.

Mercer kernels for object recognition with local features

A new class of kernels for object recognition based on local image feature representations are introduced in this paper. These kernels satisfy the Mercer condition and incorporate multiple types of local features and semilocal constraints between them. Experimental results of SVM classifiers coupled with the proposed kernels are reported on recognition tasks with the COIL-100 database and compared with existing methods. The proposed kernels achieved competitive performance and were robust to changes in object configurations and image degradations.

Steganalysis using color wavelet statistics and one-class support vector machines

Steganographic messages can be embedded into digital images in ways that are imperceptible to the human eye. These messages, however, alter the underlying statistics of an image. We previously built statistical models using first-and higher-order wavelet statistics, and employed a non-linear support vector machines (SVM) to detect steganographic messages. In this paper we extend these results to exploit color statistics, and show how a one-class SVM greatly simplifies the training stage of the classifier.

Detecting image region duplication using SIFT features

Region duplication is a common form of image manipulation where part of an image is pasted to another location to conceal undesirable contents. Most existing methods to detect region duplication are based on finding exact copies of pixel blocks, which cannot handle cases when a region is scaled or rotated before pasted to a new location. In this work, we describe a new detection method based on matching image SIFT features [6]. The robustness of the SIFT features with regards to local transforms renders this method able to detect general region duplications with efficient computation. The effectiveness of this method is demonstrated with experimental results, both qualitatively and quantitatively in terms of the detection accuracy and the false positive rate.

Nonlinear image representation using divisive normalization

In this paper, we describe a nonlinear image representation based on divisive normalization that is designed to match the statistical properties of photographic images, as well as the perceptual sensitivity of biological visual systems. We decompose an image using a multi-scale oriented representation, and use studentpsilas t as a model of the dependencies within local clusters of coefficients. We then show that normalization of each coefficient by the square root of a linear combination of the amplitudes of the coefficients in the cluster reduces statistical dependencies. We further show that the resulting divisive normalization transform is invertible and provide an efficient iterative inversion algorithm. Finally, we probe the statistical and perceptual advantages of this image representation by examining its robustness to added noise, and using it to enhance image contrast.

Nonlinear extraction of independent components of natural images using radial gaussianization

We consider the problem of efficiently encoding a signal by transforming it to a new representation whose components are statistically independent. A widely studied linear solution, known as independent component analysis (ICA), exists for the case when the signal is generated as a linear transformation of independent nongaussian sources. Here, we examine a complementary case, in which the source is nongaussian and elliptically symmetric. In this case, no invertible linear transform suffices to decompose the signal into independent components, but we show that a simple nonlinear transformation, which we call radial gaussianization (RG), is able to remove all dependencies. We then examine this methodology in the context of natural image statistics. We first show that distributions of spatially proximal bandpass filter responses are better described as elliptical than as linearly transformed independent sources. Consistent with this, we demonstrate that the reduction in dependency achieved by applying RG to either nearby pairs or blocks of bandpass filter responses is significantly greater than that achieved by ICA. Finally, we show that the RG transformation may be closely approximated by divisive normalization, which has been used to model the nonlinear response properties of visual neurons.

Steganalysis of recorded speech

Digital audio provides a suitable cover for high-throughput steganography. At 16 bits per sample and sampled at a rate of 44,100 Hz, digital audio has the bit-rate to support large messages. In addition, audio is often transient and unpredictable, facilitating the hiding of messages. Using an approach similar to our universal image steganalysis, we show that hidden messages alter the underlying statistics of audio signals. Our statistical model begins by building a linear basis that captures certain statistical properties of audio signals. A low-dimensional statistical feature vector is extracted from this basis representation and used by a non-linear support vector machine for classification. We show the efficacy of this approach on LSB embedding and Hide4PGP. While no explicit assumptions about the content of the audio are made, our technique has been developed and tested on high-quality recorded speech.