Husrev Taha Sencar

An efficient and robust method for detecting copy-move forgery

Copy-move forgery is a specific type of image tampering, where a part of the image is copied and pasted on another part of the same image. In this paper, we propose a new approach for detecting copy-move forgery in digital images, which is considerably more robust to lossy compression, scaling and rotation type of manipulations. Also, to improve the computational complexity in detecting the duplicated image regions, we propose to use the notion of counting bloom filters as an alternative to lexicographic sorting, which is a common component of most of the proposed copy-move forgery detection schemes. Our experimental results show that the proposed features can detect duplicated region in the images very accurately, even when the copied region was undergone severe image manipulations. In addition, it is observed that use of counting bloom filters offers a considerable improvement in time efficiency at the expense of a slight reduction in the robustness.

Efficient Sensor Fingerprint Matching Through Fingerprint Binarization

It is now established that photo-response nonuniformity noise pattern can be reliably used as a fingerprint to identify an image sensor. The large size and random nature of sensor fingerprints, however, make them inconvenient to store. Further, associated fingerprint matching method can be computationally expensive, especially for applications that involve large-scale databases. To address these limitations, we propose to represent sensor fingerprints in binary-quantized form. It is shown through both analytical study and simulations that the reduction in matching accuracy due to quantization is insignificant as compared to conventional approaches. Experiments on actual sensor fingerprint data are conducted to confirm that only a slight increase occurred in the probability of error and to demonstrate the computational efficacy of the approach.

Content-Based Video Copy Detection - A Survey

In the presence of overwhelming amount of digital video data, the need for automated procedures to protect owners against unauthorized use of their content. to enable content publishers and distributors to monitor broadcast usage of videos and to help businesses manage storage of videos in large databases has become ever more critical Till now, two technical approaches have been proposed toward these goals, namely, watermarking-based systems and content-based copy detection (CBCD). Among them, the former one has been more thoroughly studied and explored, while the latter one is still in its early stages. This chapter reviews existing video copy detection systems, investigates some typical CBCD algorithms, compares the algorithms through appropriate performance metrics, and lists some challenges and open issues in this research field.

Intelligent Multimedia Analysis for Security Applications

This is one of the very few books focused on analysis of multimedia data and newly emerging multimedia applications with an emphasis on security. The main objective of this project was to assemble as much research coverage as possible related to the field by defining the latest innovative technologies and providing the most comprehensive list of research references. The book includes sixteen chapters highlighting current concepts, issues and emerging technologies. Distinguished scholars from many prominent research institutions around the world contribute to the book. The book covers various aspects, including not only some fundamental knowledge and the latest key techniques, but also typical applications and open issues. Topics covered include dangerous or abnormal event detection, interaction recognition, person identification based on multiple traits, audiovisual biometric person authentication and liveness verification, emerging biometric technologies, sensitive information filtering for teleradiology, detection of nakedness in images, audio forensics, steganalysis, media content tracking authentication and illegal distributor identification through watermarking and content-based copy detection.

Audio codec identification through payload sampling

W0065 present a new method for audio codec identification that does not require decoding of coded audio data. The method utilizes randomness and chaotic characteristics of coded audio to build statistical models that represent encoding process associated with different codecs. The method is simple, as it does not assume knowledge on encoding structure of a codec. It is also fast, since it operates on a block of data, which is as small as a few kilobytes, selected randomly from the coded audio. Tests are performed to evaluate the effectiveness of the technique in identification of the codec used in encoding on both singly coded and transcoded audio samples

How to Measure Biometric Information

Being able to measure the actual information content of biometrics is very important but also a challenging problem. Main difficulty here is not only related to the selected feature representation of the biometric data, but also related to the matching algorithm employed in biometric systems. In this paper, we propose a new measure for measuring biometric information using relative entropy between intra-user and inter-user distance distributions. As an example, we evaluated the proposed measure on a face image dataset.

Methods for identifying traces of compression in audio

Compression history of an audio may reveal very useful information when traces of tampering has to be investigated or quality of an audio has to be evaluated. Motivated by this, we introduce two methods that can discriminate between single and double compressed audio and can identify compression codec and bit rate of an audio. The first method utilizes audio quality measures to realize this and operates on decoded audio. The second method, alternatively, works on coded audio, effectively the audio bit stream, and characterizes randomness and chaotic properties of the bit stream to achieve these tasks. Unlike the existing work in the literature, which are proposed mainly for MP3 encoded audio, both methods can be applied to all encoding formats. Extensive tests have been performed to test the performance of both methods under various settings. Results show that both methods can be very reliably used to obtain information on compression history of an audio.

Seam-carving based anonymization against image & video source attribution

As image source attribution techniques have become significantly sophisticated and are now becoming commonplace, there is a growing need for capabilities to anonymize images and videos. Focusing on the photo response non-uniformity noise pattern based sensor fingerprinting technique, this work evaluates the effectiveness of well-established seam carving method to defend against sensor fingerprint matching. We consider ways in which seam-carving based anonymization can be countered and propose enhancements over conventional seam carving method. Our results show that applying geometrical distortion in addition to seam carving will make counter attack very ineffective both in terms of computational complexity and accuracy.

An Ensemble of Classifiers Approach to Steganalysis

Most work on steganalysis, except a few exceptions, have primarily focused on providing features with high discrimination power without giving due consideration to issues concerning practical deployment of steganalysis methods. In this work, we focus on machine learning aspect of steganalyzer design and utilize a hierarchical ensemble of classifiers based approach to tackle two main issues. Firstly, proposed approach provides a workable and systematic procedure to incorporate several steganalyzers together in a composite steganalyzer to improve detection performance in a scalable and cost-effective manner. Secondly, since the approach can be readily extended to multi-class classification it can also be used to infer the steganographic technique deployed in generation of a stego-object. We provide results to demonstrate the potential of the proposed approach.

Carving Orphaned JPEG File Fragments

File carving techniques allow for recovery of files from storage devices in the absence of any file system metadata. When data are encoded and compressed, the current paradigm of carving requires the knowledge of the compression and encoding settings to succeed. In this paper, we advance the state of the art in JPEG file carving by introducing the ability to recover fragments of a JPEG file when the associated file header is missing. To realize this, we examined JPEG file headers of a large number of images collected from Flickr photo sharing site to identify their structural characteristics. Our carving approach utilizes this information in a new technique that performs two tasks. First, it decompresses the incomplete file data to obtain a spatial domain representation. Second, it determines the spatial domain parameters to produce a perceptually meaningful image. Recovery results on a variety of JPEG file fragments show that given the knowledge of Huffman code tables, our technique can very reliably identify the remaining decoder settings for all fragments of size 4 KiB or above. Although errors due to detection of image width, placement of image blocks, and color and brightness adjustments can occur, these errors reduce significantly when fragment sizes are >32 KiB.