Cybercrime attribution : an Eastern European case study

Phishing and related cybercrime is responsible for billions of dollars in losses annually. Gartner reported more than 5 million U.S. consumers lost money to phishing attacks in the 12 months ending in September 2008 (Gartner 2009). This paper asks whether the majority of organised phishing and related cybercrime originates in Eastern Europe rather than elsewhere such as China or the USA. The Russian “Mafiya” in particular has been popularised by the media and entertainment industries to the point where it can be hard to separate fact from fiction but we have endeavoured to look critically at the information available on this area to produce a survey. We take a particular focus on cybercrime from an Australian perspective, as Australia was one of the first places where Phishing attacks against Internet banks were seen. It is suspected these attacks came from Ukrainian spammers. The survey is built from case studies both where individuals from Eastern Europe have been charged with related crimes or unsolved cases where there is some nexus to Eastern Europe. It also uses some earlier work done looking at those early Phishing attacks, archival analysis of Phishing attacks in July 2006 and new work looking at correlation between the Corruption Perception Index, Internet penetration and tertiary education in Russia and the Ukraine. The value of this work is to inform and educate those charged with responding to cybercrime where a large part of the problem originates and try to understand why.

Short utterance PLDA speaker verification using SN-WLDA and variance modelling techniques

This paper proposes a combination of source-normalized weighted linear discriminant analysis (SN-WLDA) and short utterance variance (SUV) PLDA modelling to improve the short utterance PLDA speaker verification. As short-length utterance i-vectors vary with the speaker, session variations and phonetic content of the utterance (utterance variation), a combined approach of SN-WLDA projection and SUV PLDA modelling is used to compensate the session and utterance variations. Experimental studies have found that a combination of SN-WLDA and SUV PLDA modelling approach shows an improvement over baseline system (WCCN[LDA]-projected Gaussian PLDA (GPLDA)) as this approach effectively compensates the session and utterance variations.

A speaker rediarization scheme for improving diarization in large two-speaker telephone datasets

In this paper we propose a novel scheme for carrying out speaker diarization in an iterative manner. We aim to show that the information obtained through the first pass of speaker diarization can be reused to refine and improve the original diarization results. We call this technique speaker rediarization and demonstrate the practical application of our rediarization algorithm using a large archive of two-speaker telephone conversation recordings. We use the NIST 2008 SRE summed telephone corpora for evaluating our speaker rediarization system. This corpus contains recurring speaker identities across independent recording sessions that need to be linked across the entire corpus. We show that our speaker rediarization scheme can take advantage of inter-session speaker information, linked in the initial diarization pass, to achieve a 30% relative improvement over the original diarization error rate (DER) after only two iterations of rediarization.

An iterative speaker re-diarization scheme for improving speaker-based entity extraction in multimedia archives

In this paper we present a novel scheme for improving speaker diarization by making use of repeating speakers across multiple recordings within a large corpus. We call this technique speaker re-diarization and demonstrate that it is possible to reuse the initial speaker-linked diarization outputs to boost diarization accuracy within individual recordings. We first propose and evaluate two novel re-diarization techniques. We demonstrate their complementary characteristics and fuse the two techniques to successfully conduct speaker re-diarization across the SAIVT-BNEWS corpus of Australian broadcast data. This corpus contains recurring speakers in various independent recordings that need to be linked across the dataset. We show that our speaker re-diarization approach can provide a relative improvement of 23% in diarization error rate (DER), over the original diarization results, as well as improve the estimated number of speakers and the cluster purity and coverage metrics.

Rescaling clustering trees using impact ratios for robust hierarchical speaker clustering

We present a novel method for improving hierarchical speaker clustering in the tasks of speaker diarization and speaker linking. In hierarchical clustering, a tree can be formed that demonstrates various levels of clustering. We propose a ratio that expresses the impact of each cluster on the formation of this tree and use this to rescale cluster scores. This provides score normalisation based on the impact of each cluster. We use a state-of-the-art speaker diarization and linking system across the SAIVT-BNEWS corpus to show that our proposed impact ratio can provide a relative improvement of 16% in diarization error rate (DER).

Speaker verification using I-vector features

This PhD research has provided novel solutions to three major challenges which have prevented the wide spread deployment of speaker recognition technology: (1) combating enrolment/ verification mismatch, (2) reducing the large amount of development and training data that is required and (3) reducing the duration of speech required to verify a speaker. A range of applications of speaker recognition technology from forensics in criminal investigations to secure access in banking will benefit from the research outcomes.

Humanizing the self: Moderators of the attribution of lesser humanness to others

Three studies investigated moderators of the tendency to attribute greater humanness to the self than to others, an interpersonal counterpart of outgroup infra-humanization. Study 1 demonstrated that this self-humanizing effect is reduced when the other is the focus of comparison. Study 2 showed that the effect is reduced when the other is individuated. Study 3 indicated that empathy does not moderate self-humanizing: Self-humanizing failed to correlate negatively with dispositional empathy or perspective-taking. Study 3 also indicated that abstract construal moderates the self-humanizing effect using a temporal comparison. Participants rated their future self, but not their past self, as less human than their present self. Studies 1 and 3 also showed that selfhumanizing is greater for undesirable traits: People may view their failings as “only human.” All findings were distinct from those attributable to self-enhancement. Self-humanizing may reflect a combination of egocentrism, focalism, abstract representation of others, and motivated processes.

Improving out-domain PLDA speaker verification using unsupervised inter-dataset variability compensation approach

Experimental studies have found that when the state-of-the-art probabilistic linear discriminant analysis (PLDA) speaker verification systems are trained using out-domain data, it significantly affects speaker verification performance due to the mismatch between development data and evaluation data. To overcome this problem we propose a novel unsupervised inter dataset variability (IDV) compensation approach to compensate the dataset mismatch. IDV-compensated PLDA system achieves over 10% relative improvement in EER values over out-domain PLDA system by effectively compensating the mismatch between in-domain and out-domain data.

Improving PLDA speaker verification using WMFD and linear-weighted approaches in limited microphone data conditions

This paper proposes the addition of a weighted median Fisher discriminator (WMFD) projection prior to length-normalised Gaussian probabilistic linear discriminant analysis (GPLDA) modelling in order to compensate the additional session variation. In limited microphone data conditions, a linear-weighted approach is introduced to increase the influence of microphone speech dataset. The linear-weighted WMFD-projected GPLDA system shows improvements in EER and DCF values over the pooled LDA- and WMFD-projected GPLDA systems in inter-view-interview condition as WMFD projection extracts more speaker discriminant information with limited number of sessions/ speaker data, and linear-weighted GPLDA approach estimates reliable model parameters with limited microphone data.

Dataset-invariant covariance normalization for out-domain PLDA speaker verification

In this paper we introduce a novel domain-invariant covariance normalization (DICN) technique to relocate both in-domain and out-domain i-vectors into a third dataset-invariant space, providing an improvement for out-domain PLDA speaker verification with a very small number of unlabelled in-domain adaptation i-vectors. By capturing the dataset variance from a global mean using both development out-domain i-vectors and limited unlabelled in-domain i-vectors, we could obtain domain- invariant representations of PLDA training data. The DICN- compensated out-domain PLDA system is shown to perform as well as in-domain PLDA training with as few as 500 unlabelled in-domain i-vectors for NIST-2010 SRE and 2000 unlabelled in-domain i-vectors for NIST-2008 SRE, and considerable relative improvement over both out-domain and in-domain PLDA development if more are available.

The QUT-NOISE-SRE protocol for the evaluation of noisy speaker recognition

The QUT-NOISE-SRE protocol is designed to mix the large QUT-NOISE database, consisting of over 10 hours of back- ground noise, collected across 10 unique locations covering 5 common noise scenarios, with commonly used speaker recognition datasets such as Switchboard, Mixer and the speaker recognition evaluation (SRE) datasets provided by NIST. By allowing common, clean, speech corpora to be mixed with a wide variety of noise conditions, environmental reverberant responses, and signal-to-noise ratios, this protocol provides a solid basis for the development, evaluation and benchmarking of robust speaker recognition algorithms, and is freely available to download alongside the QUT-NOISE database. In this work, we use the QUT-NOISE-SRE protocol to evaluate a state-of-the-art PLDA i-vector speaker recognition system, demonstrating the importance of designing voice-activity-detection front-ends specifically for speaker recognition, rather than aiming for perfect coherence with the true speech/non-speech boundaries.

A comparative study of speaker adaptation methods

For the problem of speaker adaptation in speech recognition, the performance depends on the availability of adaptation data. In this paper, we have compared several existing speaker adaptation methods, viz. maximum likelihood linear regression (MLLR), eigenvoice (EV), eigenspace-based MLLR (EMLLR), segmental eigenvoice (SEV) and hierarchical eigenvoice (HEV) based methods. We also develop a new method by modifying the existing HEV method for achieving further performance improvement in a limited available data scenario. In the sense of availability of adaptation data, the new modified HEV (MHEV) method is shown to perform better than all the existing methods throughout the range of operation except the case of MLLR at the availability of more adaptation data.

Hugo Steiner-Prag approaching speaker's lectern at the International Book Arts Exhibition; Leipzig.

Digital Image

Deploying speaker verification techniques to vision-based RPA detect and avoid

Detect and Avoid (DAA) technology is widely acknowledged as a critical enabler for unsegregated Remote Piloted Aircraft (RPA) operations, particularly Beyond Visual Line of Sight (BVLOS). Image-based DAA, in the visible spectrum, is a promising technological option for addressing the challenges DAA presents. Two impediments to progress for this approach are the scarcity of available video footage to train and test algorithms, in conjunction with testing regimes and specifications which facilitate repeatable, statistically valid, performance assessment. This paper includes three key contributions undertaken to address these impediments. In the first instance, we detail our progress towards the creation of a large hybrid collision and near-collision encounter database. Second, we explore the suitability of techniques employed by the biometric research community (Speaker Verification and Language Identification), for DAA performance optimisation and assessment. These techniques include Detection Error Trade-off (DET) curves, Equal Error Rates (EER), and the Detection Cost Function (DCF). Finally, the hybrid database and the speech-based techniques are combined and employed in the assessment of a contemporary, image based DAA system. This system includes stabilisation, morphological filtering and a Hidden Markov Model (HMM) temporal filter.