Elena Vildjiounaite

Bio: Elena Vildjiounaite is an academic researcher from VTT Technical Research Centre of Finland. The author has contributed to research in topics: Context (language use) & Context awareness. The author has an hindex of 4, co-authored 6 publications receiving 139 citations.

Privacy, identity and security in ambient intelligence: a scenario analysis

Abstract: The success of ambient intelligence (AmI) will depend on how secure it can be made, how privacy and other rights of individuals can be protected and how individuals can come to trust the intelligent world that surrounds them and through which they move. This article addresses these issues by analysing scenarios for ambient intelligence applications that have been developed over the last few years. It elaborates the assumptions that promotors make about the likely use of the technology and possibly unwanted side effects. It concludes with a number of threats for personal privacy that become evident.

Increasing Security of Mobile Devices by Decreasing User Effort in Verification

Abstract: Reliable user verification is important for security of computers and personal devices; however, most of well-performing verification methods require explicit user effort. As a consequence, an access is granted for a long time after the only successful verification, which allows replacing the authorized user to the advantage of an impostor, as it is often the case with mobile phones. This work proposes a method of frequent user verification, based on cascading of unobtrusive biometrics with more reliable biometrics, provided explicitly, in such a way that explicit effort is required only if unobtrusive verification fails. Experiments with voice, gait and fingerprint data have shown that in most of noise conditions cascade was able to satisfy security requirements of False Accept Rate 1% and to achieve overall False Reject Rate 3% or less, while requiring explicit effort in 10 - 60% of cases.

Context-Dependent User Modelling for Smart Homes

Abstract: This works presents a user modelling service for a Smart Home --- intelligent context-aware environment, providing personalized proactive support to its inhabitants. Diversity of Smart Home applications imposes various technical and implementation requirements, such as the need to model dependency of user preferences on context in a unified and convenient way, both for users and for application developers. This paper introduces the service architecture and currently implemented functionalities: stereotypes-based profiles initialisation; a GUI for acquisition of context-dependent and context-independent preferences, which provides an easy way to create own concepts of context ontology and to map them into already existing concepts; and a method to learn context-dependent user preferences from interaction history.

A layered approach to context-dependent user modelling

Abstract: This works presents a method for explicit acquisition of context-dependent user preferences (preferences which change depending on a user situation, e.g., higher interest in outdoor activities if it is sunny than if it is raining) for Smart Home - intelligent environment, which recognises contexts of its inhabitants (such as presence of people, activities, events, weather etc) via home and mobile devices and provides personalized proactive support to the users. Since a set of personally important situations, which affect user preferences, is user-dependent, and since many situations can be described only in fuzzy terms, we provide users with an easy way to develop personal context ontology and to map it fuzzily into common ontology via GUI. Backward mapping, by estimating the probability of occurrence of a user-defined situation, allows retrieval of preferences from all components of the user model.

Unobtrusive User-Authentication on Mobile Phones Using Biometric Gait Recognition

Abstract: The need for more security on mobile devices is increasing with new functionalities and features made available. To improve the device security we propose gait recognition as a protection mechanism. Unlike previous work on gait recognition, which was based on the use of video sources, floor sensors or dedicated high-grade accelerometers, this paper reports the performance when the data is collected with a commercially available mobile device containing low-grade accelerometers. To be more specific, the used mobile device is the Google G1 phone containing the AK8976A embedded accelerometer sensor. The mobile device was placed at the hip on each volunteer to collect gait data. Preproccesing, cycle detection and recognition-analysis were applied to the acceleration signal. The performance of the system was evaluated having 51 volunteers and resulted in an equal error rate (EER) of 20%.

Code and Other Laws of Cyberspace

Abstract: Code and Other Laws of Cyberspace. Lawrence Lessig. New York: Basic Books, 1999. 230 pp. $21 hbk. Lawrence Lessig's Code and Other Laws of Cyberspace is perhaps the most original book yet written about cyberspace law. With an accessible style that is rich in anecdotes and metaphors and surprisingly low on legal and technical jargon, Lessig, a constitutional law scholar at Harvard and a consultant on the Microsoft antitrust case, writes for a wide scholarly audience. Even more than the recent The Control Revolution (New York: Century Foundation, 1999) by Andrew Shapiro, Lessig has managed to write about a rapidly evolving subject at a level of abstraction and theoretical sophistication that ensures that his contribution will long remain relevant. Central to Lessig's theoretical framework is his breakdown of four modalities of regulation: law, economic markets, norms, and an intriguing category he calls "architecture." Architecture includes constraints that the natural world imposes or that people construct-for example, speed bumps on roads. The architecture in cyberspace is computer code: code constructs the cyber-world. Consider the example of pornography regulation. Lessig contrasts how these four modalities of regulation control access to pornography in "real space" and in cyberspace, vividly demonstrating why a simple translation of existing law from "real space" to cyberspace is often impossible. In real space, pornography is extensively regulated through all four modalities, in ways that limit children's access to it. Laws require that vendors sell pornography only to adults. Markets prevent children from accessing pornography because it costs money. Norms help limit children's access to pornography, both by stigmatizing pornography and stigmatizing dealers who would sell it to children. In the category of real space "architecture," there is the simple matter of how a child is: even if a child attempted to disguise himself as an adult, he would probably notbe successful at fooling a salesperson. These four kinds of constraints may be imperfect, but are reasonably effective in limiting children's access to pornography in real space, Lessig contends. In cyberspace, however, the modalities of regulation of pornography operate differently and less effectively. Law is unsettled. Markets are different in at least two ways: distribution of digital files is much cheaper than distribution of printed material or videos, and though there are plenty of commercial pornography sites, much pornography can be accessed at no cost through newsgroups. Differences in the "architecture" of cyberspace are crucial because they allow faceless transactions. Faceless transactions may make disguising identity and age simple, therefore allowing a child to avoid the restrictions of law and norms. Thus the "real space" regulatory regime is upset, making pornography generally more available to children in cyberspace. Ways of filtering content or zoning the Internet are now extensively debated, but no simple transfer of the offline constraints to cyberspace seems possible. As he applies his theory to pornography regulation and the regulation of intellectual property and privacy, Lessig emphasizes that not only the codes of law but computer codethe "architecture" of cyberspace-an "embed" values and enable government and private actors to control behavior. …

Biometric recognition by gait: A survey of modalities and features

Abstract: The scientific literature on automated gait analysis for human recognition has grown dramatically over the past 15 years. A number of sensing modalities including those based on vision, sound, pressure, and accelerometry have been used to capture gait information. For each of these modalities, a number of methods have been developed to extract and compare human gait information, resulting in different sets of features. This paper provides an extensive overview of the various types of features that have been utilized for each sensing modality and their relationship to the appearance and biomechanics of gait. The features considered in this work include (a) static and dynamic (temporal) features; (b) model-based and model-free visual features; (c) ground reaction force-based and finely resolved underfoot pressure features; (d) wearable sensor features; and (e) acoustic features. We also review the factors that impact gait recognition, and discuss recent work on gait spoofing and obfuscation. Finally, we enumerate the challenges and open problems in the field of gait recognition.

Personalization and user verification in wearable systems using biometric walking patterns

Abstract: In this article, a novel technique for user's authentication and verification using gait as a biometric unobtrusive pattern is proposed. The method is based on a two stages pipeline. First, a general activity recognition classifier is personalized for an specific user using a small sample of her/his walking pattern. As a result, the system is much more selective with respect to the new walking pattern. A second stage verifies whether the user is an authorized one or not. This stage is defined as a one-class classification problem. In order to solve this problem, a four-layer architecture is built around the geometric concept of convex hull. This architecture allows to improve robustness to outliers, modeling non-convex shapes, and to take into account temporal coherence information. Two different scenarios are proposed as validation with two different wearable systems. First, a custom high-performance wearable system is built and used in a free environment. A second dataset is acquired from an Android-based commercial device in a `wild' scenario with rough terrains, adversarial conditions, crowded places and obstacles. Results on both systems and datasets are very promising, reducing the verification error rates by an order of magnitude with respect to the state-of-the-art technologies.

Internet of Things Forensics: Challenges and approaches

Abstract: The scope of this paper is two-fold: firstly it proposes the application of a 1-2-3 Zones approach to Internet of Things (IoT)-related Digital Forensics (DF) investigations. Secondly, it introduces a Next-Best-Thing Triage (NBT) Model for use in conjunction with the 1-2-3 Zones approach where necessary and vice versa. These two `approaches' are essential for the DF process from an IoT perspective: the atypical nature of IoT sources of evidence (i.e. Objects of Forensic Interest - OOFI), the pervasiveness of the IoT environment and its other unique attributes - and the combination of these attributes - dictate the necessity for a systematic DF approach to incidents. The two approaches proposed are designed to serve as a beacon to incident responders, increasing the efficiency and effectiveness of their IoT-related investigations by maximizing the use of the available time and ensuring relevant evidence identification and acquisition. The approaches can also be applied in conjunction with existing, recognised DF models, methodologies and frameworks.