Aravind K. Mikkilineni

Scanner identification using sensor pattern noise

Digital images can be captured or generated by a variety of sources including digital cameras and scanners. In many cases it is important to be able to determine the source of a digital image. This paper presents methods for authenticating images that have been acquired using flatbed desktop scanners. The method is based on using the pattern noise of the imaging sensor as a fingerprint for the scanner, similar to methods that have been reported for identifying digital cameras. To identify the source scanner of an image a reference pattern is estimated for each scanner and is treated as a unique fingerprint of the scanner. An anisotropic local polynomial estimator is used for obtaining the reference patterns. To further improve the classification accuracy a feature vector based approach using an SVM classifier is used to classify the pattern noise. This feature vector based approach is shown to achieve a high classification accuracy.

Printer identification based on graylevel co-occurrence features for security and forensic applications

In todays digital world securing different forms of content is very important in terms of protecting copyright and verifying authenticity. Many techniques have been developed to protect audio, video, digital documents, images, and programs (executable code). One example is watermarking of digital audio and images. We believe that a similar type of protection for printed documents is very important. The goals of our work are to securely print and trace documents on low cost consumer printers such as inkjet and electrophotographic (laser) printers. We will accomplish this through the use of intrinsic and extrinsic features obtained from modelling the printing process. In this paper we describe the use of image texture analysis to identify the printer used to print a document. In particular we will describe a set of features that can be used to provide forensic information about a document. We will demonstrate our methods using 10 EP printers.

Scanner Identification Using Feature-Based Processing and Analysis

Digital images can be obtained through a variety of sources including digital cameras and scanners. In many cases, the ability to determine the source of a digital image is important. This paper presents methods for authenticating images that have been acquired using flatbed desktop scanners. These methods use scanner fingerprints based on statistics of imaging sensor pattern noise. To capture different types of sensor noise, a denoising filterbank consisting four different denoising filters is used for obtaining the noise patterns. To identify the source scanner, a support vector machine classifier based on these fingerprints is used. These features are shown to achieve high classification accuracy. Furthermore, the selected fingerprints based on statistical properties of the sensor noise are shown to be robust under postprocessing operations, such as JPEG compression, contrast stretching, and sharpening.

Printer and scanner forensics

Contrary to popular opinion, the use of paper in our society will not disappear during the foreseeable future. In fact, paper use continues to grow rather than decline. It is certainly true that as individuals, we may be printing less than we used to. And the role of paper has been transformed from the archival record of a document to a convenient and aesthetically appealing graphical user interface. The use of paper is now intimately linked to the electronic systems that capture, process, transmit, generate, and reproduce textual and graphic content. Paper can be thought of as an interface between humans and the digital world. If this interface is not secure, the entire system becomes vulnerable to attack and abuse. Although paper is read by humans in the same way that it has been for millennia and has had the same fundamental form and composition for almost that long, the technologies for printing and scanning documents and capturing their content have evolved tremendously, especially during the last 20 years. This has moved the capability to generate printed documents from the hands of a select few to anyone with access to low-cost scanners, printers, and personal computers. It has greatly broadened the opportunities for abuse of trust through the generation of fallacious documents and the tampering with existing documents, including the embedding of messages in these documents.

Forensic classification of imaging sensor types

Digital images can be captured or generated by a variety of sources including digital cameras and scanners. In many cases it is important to be able to determine the source of a digital image. Methods exist to authenticate images generated by digital cameras or scanners, however they rely on prior knowledge of the image source (camera or scanner). This paper presents methods for determining the class of the image source (camera or scanner). The method is based on using the differences in pattern noise correlations that exist between digital cameras and scanners. To improve the classification accuracy a feature vector based approach using an SVM classifier is used to classify the pattern noise.

Survey of Scanner and Printer Forensics at Purdue University

This paper describes methods for forensic characterization of scanners and printers. This is important in verifying the trust and authenticity of data and the device that created it. An overview of current forensic methods, along with current improvements of these methods is presented. Near-perfect identification of source scanner and printer is shown to be possible using these techniques.

Forensics of Things

In this paper we describe methods for forensic characterization of devices. This is important in verifying the trust and authenticity of data and the device that created it. We present and examine current forensic identification techniques for RF devices, printers, cameras, and show how these techniques can be generalized for use with other devices

Information embedding and extraction for electrophotographic printing processes

In todays digital world securing different forms of content is very important in terms of protecting copyright and verifying authenticity. One example is watermarking of digital audio and images. We believe that a marking scheme analogous to digital watermarking but for documents is very important. In this paper we describe the use of laser amplitude modulation in electrophotographic printers to embed information in a text document. In particular we describe an embedding and detection process which allows the embedding of 1 bit in a single line of text. For a typical 12 point document, 33 bits can be embedded per page.

Situational Awareness and Visual Analytics for Emergency Response and Training

Many emergency response units are currently faced with restrictive budgets which prohibit their use of technology both in training and in real-world situations. Our work focuses on creating an affordable, mobile, state-of-the-art emergency response test-bed through the integration of low-cost, commercially available products. We have developed a command, control, communications, surveillance and reconnaissance system that will allow small-unit exercises to be tracked and recorded for evaluation purposes. Our system can be used for military and first responder training providing the nexus for decision making through the use of computational models, advanced technology, situational awareness and command and control. During a training session, data is streamed back to a central repository allowing commanders to evaluate their squads in a live action setting and assess their effectiveness in an after-action review. In order to effectively analyze this data, an interactive visualization system has been designed in which commanders can track personnel movement, view surveillance feeds, listen to radio traffic, and fast-forward/rewind event sequences. This system provides both 2-D and 3-D views of the environment while showing previously traveled paths, responder orientation and activity level. Both stationary and personnel-worn mobile camera video feeds may be displayed, as well as the associated radio traffic.

Texture based attacks on intrinsic signature based printer identification

Several methods exist for printer identification from a printed document. We have developed a system that performs printer identification using intrinsic signatures of the printers. Because an intrinsic signature is tied directly to the electromechanical properties of the printer, it is difficult to forge or remove. There are many instances where existance of the intrinsic signature in the printed document is undesireable. In this work we explore texture based attacks on intrinsic printer identification from text documents. An updated intrinsic printer identification system is presented that merges both texture and banding features. It is shown that this system is scable and robust against several types of attacks that one may use in an attempt to obscure the intrinsic signature.