A large amount of digital information collected and stored in datasets creates vast opportunities for knowledge discovery and data mining. These datasets, however, may contain sensitive information about individuals and, therefore, it is imperative to ensure that their privacy is protected. Most research in the area of privacy preserving data publishing does not make any assumptions about an intended analysis task applied on the dataset. In many domains such as healthcare, finance, etc; however, it is possible to identify the analysis task beforehand. Incorporating such knowledge of the ultimate analysis task may improve the quality of the anonymized data while protecting the privacy of individuals. Furthermore, the existing research which consider the ultimate analysis task (e.g., classification) is not suitable for high-dimensional data. We show that automatic feature selection (which is a well-known dimensionality reduction technique) can be utilized in order to consider both aspects of privacy and utility simultaneously. In doing so, we show that feature selection can enhance existing privacy preserving techniques addressing k-anonymity and differential privacy and protect privacy while reducing the amount of modifications applied to the dataset; hence, in most of the cases achieving higher utility. We consider incorporating the concept of privacy-by-design within the feature selection process. We propose techniques that turn filter-based and wrapper-based feature selection into privacy-aware processes. To this end, we build a layer of privacy on top of regular feature selection process and obtain a privacy preserving feature selection that is not only guided by accuracy but also the amount of protected private information. In addition to considering privacy after feature selection we introduce a framework for a privacy-aware feature selection evaluation measure. That is, we incorporate privacy during feature selection and obtain a list of candidate privacy-aware attribute subsets that consider (and satisfy) both efficacy and privacy requirements simultaneously. Finally, we propose a multi-dimensional, privacy-aware evaluation function which incorporates efficacy, privacy, and dimensionality weights and enables the data holder to obtain a best attribute subset according to its preferences.

The convergence of transport, communication, computing and positioning technologies has enabled a smart car revolution. As a result, pricing of roads based on telematics technologies has gained significant attention. While there are promised benefits, systematic disclosure of precise location has the ability to impinge on privacy of a special kind, known as location privacy. The aim of this thesis is to provide technical designs that enhance the location privacy of motorists without compromising the benefits of accurate pricing. However, this research looks beyond a solely technology-based solution, For example, the ethical implications of the use of GPS data in pricing models have not been fully understood. Likewise. minimal research exists to evaluate the technical vulnerabilities that could be exploited to avoid criminal or financial penalties. To design a privacy-aware system, it is important to understand the needs of the stakeholders, most importantly the motorists. Knowledge about the anticipated privacy preferences of motorists is important in order to make reasonable predictions about their future willingness to adopt these systems. There is limited research so far Otl user perceptions regarding specific payment options in the uptake of privacy-aware systems. This thesis provides a critical privacy assessment of two mobility pricing systems, namely electronic tolls and mobility-priced insurance. As a result of this assessment. policy recommendations arc developed which could support a common approach in facilitating privacy-aware mobility-pricing strategies. This thesis also evaluates the existing and potential inferential threats and vulnerabilities to develop security and privacy recommendations for privacy-aware pricing designs for tolls and insurance. Utilising these policy recommendations and analysing user-perception with regards to the feasibility of sustaining privacy and willingness to pay for privacy, two privacy-aware mobility pricing designs have been presented which bridge the entire array of privacy interests and bring them together into a unified approach capable of sustaining legal protection as well as satisfying privacy requirements of motorists. It is maintained that it is only by social and technical analysis working in tandem that critical privacy issues in relation to location can be addressed.

People are nomadic; traveling from place to place. As a user travels, he may need access to his digital information, including his data, applications, and settings. A convenient way to supply this access is to have the user carry that digital information in a portable computer such as a laptop or smart phone. As Moore's Law continues to operate, devices such as smart phones can easily perform the computing necessary for a user's work. Unfortunately, the amount of data a human can receive and convey through such devices is limited. To receive more information humans require more screen real estate. To transmit more information humans need rich input devices like mice and full-sized keyboards. To allow users to carry their digital information in a small device while maintaining opportunities for rich input, this research takes the approach of allowing users to carry a small portable device and then annex screens, keyboards, and mice whenever those devices are available in a user's environment. This research pursued the "carry it with you" paradigm first by building an ideal annexing framework which helps maximize the screen real estate while minimizing the resources—RAM, CPU, and wireless radio—consumed on the personal device. The resource consumption is demonstrated through a comparison with existing remote rendering technologies. Next, a privacy-aware framework was added to the annexing framework to help protect the user's sensitive data from damage and theft when he annexes a potentially malicious device. A framework like this has not existed before, and this research shows how the user's sensitive data is protected by this framework. Third, legacy machines and software are allowed to participate in the carry-it-with-you experience by scraping pixels from the user's existing applications and transmitting those pixels to an annexed display. Finally, when a user encounters a display space he does not own, but which he needs to control (e.g. by preventing anyone else from annexing it simultaneously, or by constraining each user to a different section of the display space), rather than forcing the user to learn and use control software supplied by the display, the user can bring his own control software and use it to enforce the user's desired control paradigm. This dissertation shows the carry-it-with-you paradigm is a powerful potential avenue which allows users to confidently use display spaces with varying configurations in an assortment of environments.

Les usages dans le domaine des systèmes multi-agents ont évolué de manière à intégrer davantage les utilisateurs humains dans les applications. La manipulation d'informations privées par des agents autonomes appelle alors à une protection adaptée des données personnelles. Les présents travaux examinent d'abord le contexte légal de la protection de la vie privée, ainsi que<br />les divers moyens informatiques destinés à la protection des données personnelles. Il en ressort un besoin de solutions fondées sur les méthodes d'IA, autorisant à la fois un raisonnement sur les réglementations et l'adaptation du comportement d'un agent à ces réglementations. Dans cette perspective, nous proposons le modèle d'agent PAw (Privacy-Aware) et la logique DLP (Deontic Logic for Privacy), conçue pour traiter des réglementations provenant d'autorités multiples. Le composant de raisonnement normatif de l'agent analyse son contexte hétérogène et fournit une politique cohérente pour le traitement des données personnelles. L'agent PAw contrôle alors automatiquement sa propre utilisation des données en regard de cette politique. Afin d'appliquer cette politique de manière distante, nous étudions les différentes architectures d'applications distribuées orientées vers la protection de la vie privée, notamment celles fondées sur les principes du Trusted Computing. Nous en proposons une complémentaire, illustrant la possibilité d'utiliser différemment cette technologie. L'implémentation de l'agent PAw permet la démonstration de ses principes sur trois scénarios, montrant ainsi l'adaptabilité de l'agent à son contexte normatif et l'influence des réglementations sur le comportement de l'application.

No description available.