Andrea Oermann

Digital audio forensics: a first practical evaluation on microphone and environment classification

In this paper a first approach for digital media forensics is presented to determine the used microphones and the environments of recorded digital audio samples by using known audio steganalysis features. Our first evaluation is based on a limited exemplary test set of 10 different audio reference signals recorded as mono audio data by four microphones in 10 different rooms with 44.1 kHz sampling rate and 16 bit quantisation. Note that, of course, a generalisation of the results cannot be achieved. Motivated by the syntactical and semantical analysis of information and in particular by known audio steganalysis approaches, a first set of specific features are selected for classification to evaluate, whether this first feature set can support correct classifications. The idea was mainly driven by the existing steganalysis features and the question of applicability within a first and limited test set. In the tests presented in this paper, an inter-device analysis with different device characteristics is performed while intra-device evaluations (identical microphone models of the same manufacturer) are not considered. For classification the data mining tool WEKA with K-means as a clustering and Naive Bayes as a classification technique are applied with the goal to evaluate their classification in regard to the classification accuracy on known audio steganalysis features. Our results show, that for our test set, the used classification techniques and selected steganalysis features, microphones can be better classified than environments. These first tests show promising results but of course are based on a limited test and training set as well a specific test set generation. Therefore additional and enhanced features with different test set generation strategies are necessary to generalise the findings.

Sensometrics: Identifying Pen Digitizers by Statistical Multimedia Signal Processing

In this paper a new approach will be introduced to identify pen-based digitizer devices based on handwritten samples used for biometric user authentication. This new method of digitizer identification based on their signal properties can also be seen as an influencing part in the new research area of so-called sensometrics. The goal of the work presented in this paper is to identify statistical features, derived from signals provided by pen-based digitizer tablets during the writing process, which allow identification, or at least group discrimination of different device types. Based on a database of a total of approximately 40,000 writing samples taken on 23 different pen digitizers, specific features for class discrimination will be chosen and a novel feature vector based classification system will be implemented and experimentally validated. The goal of our experimental validation is to study the class space that can be obtained, given a specific feature set, i.e. to which degree single tablets and/or groups of pen digitizers can be identified using our developed classification by a decision tree model. The results confirm that a group discrimination of devices can be achieved. By applying this new approach, the 23 different tablets from our database can be discriminated in 19 output groups.

A Cross-cultural Evaluation Framework for Behavioral Biometric User Authentication

Today biometric techniques are based either on passive (e.g. IrisScan, Face) or active methods (e.g. voice and handwriting). In our work we focus on evaluation of the latter. These methods, also described as behavioral Biometric, are characterized by a trait that is learnt and acquired over time. Several approaches for user authentication have been published, but today they have not yet been evaluated under cultural aspects such as language, script and personal background of users. Especially for handwriting such cultural aspects can lead to a significant and essential outcome, as different spoken and written languages are being used and also the script used for handwriting is different in nature.

Semantic fusion for biometric user authentication as multimodal signal processing

Today the application of multimodal biometric systems is a common way to overcome the problems, which come with unimodal systems, such as noisy data, attacks, overlapping of similarities, and non-universality of biometric characteristics. In order to fuse multiple identification sources simultaneously, fusion strategies can be applied on different levels. This paper presents a theoretical concept of a methodology to improve those fusions and strategies independently of their application levels. By extracting and merging certain semantic information and integrating it as additional knowledge (e.g. metadata) into the process the fusion can be potentially improved. Thus, discrepancies and irregularities of one biometric trait can be verified by another one and signal errors can be identified and corrected.

Verifier-tuple as a classifier for biometric handwriting authentication: combination of syntax and semantics

In this paper, a new concept for classifying handwriting data and its analysis for biometric user authentication is presented. The concepts characteristic is the combination of syntax and semantics. It implies a determination of four distinct levels of syntax and semantics to lower complexity and structure information. We demonstrate the concepts impacts on on-line handwritings and the user verification, and clarify the benefit of applying information of higher levels of semantics within the authentication methods. As a result we are able to evaluate techniques for biometric user authentication. Furthermore, we precisely outline and reason a more accurate biometric user authentication system, due to the classification given by the Verifier-Tuple concept.

Vertrauenswürdige und abgesicherte Langzeitarchivierung multimedialer Inhalte

Inhaltsverzeichnis Inhaltsverzeichnis 1 Einleitung, Motivation und Überblick 1

Concept for Audio Quality and Security Assurance in Mobile Phones as Multimodal User Guides

This paper presents a new concept of an approach to evaluate the assurance of the audio quality and its impact on the security of mobile phones used as multimodal user guides at the same time. Differently caused interferences can influence the subjectively perceived audio signal. Finding objective measure values acts as the motivation for the development of the presented model. This model to evaluate audio codecs in relation to three defined and interdependent challenges, addressing three different kinds of problems - technical, environmental, and security, will be introduced while its evaluation is in progress. As a result, our model, which is still work in process, will help to provide recommendations to future developments and to establish standardizations in the field of multimodal user guides