scispace - formally typeset
Search or ask a question
Book ChapterDOI

Proposed Use of Information Dispersal Algorithm in User Profiling

TL;DR: The algorithm for privacy and security purpose of different profiles, with the integration of Information Dispersal Algorithm is proposed, which would be achieved by the use of the private cloud.
Abstract: For recommending the best result to the user as per his requirement, User Profiling plays an important role. In user profiling, the profiles are created from the past data of same user. Maintaining the security and privacy of this data becomes a big challenge for researchers. Here, we are proposing the algorithm for privacy and security purpose of different profiles, with the integration of Information Dispersal Algorithm. The use of vast data of profiles by the user from any location at any time would be achieved by the use of the private cloud. As the profiles of different devices are maintained on the central cloud server, the recommendation for user for particular device can be executed easily.
Citations
More filters
Journal ArticleDOI
TL;DR: This paper has shown how simple browsing log data can jeopardize the identity and the personal integrity of a person along with analysis of preventive measures to protect them.
Abstract: Personalization security is a concern with the rising ability to monitor and access public and personal data by organizations, mainly with gradual integration of human life with their devices. In this paper we have shown how simple browsing log data can jeopardize the identity and the personal integrity of a person along with analysis of preventive measures to protect them. As people get digitally enslaved, unknowingly browsing logs inherited certain unique behaviors of the people. It can be characterized and used for monitoring them and their aligned social, professional and organizational counterparts. It is quite a challenge for modern systems to keep attackers at bay and prevent them from gathering and analyzing activity data which can be used to identify specific, easy and valuable targets. Our analysis is based on modeling efficient systems for justification of the possible vulnerabilities and counter-measures through data driven approaches to learn and analyze such data and derive the extent these data can be exploited. Overall, we achieved an accuracy of 85% for identification of targeted characteristics using log data features using deep learning models, which achieved better than other learning models, thus effectively pointing out to the fact that there is severe non-linearity and combination possibilities in the data.

13 citations

Book ChapterDOI
01 Jan 2021
TL;DR: In this paper, the performance of four popular machine learning classification algorithms (Naive Bayes, decision trees, logistic regression, and random forest) on two popular benchmarked datasets (wine quality dataset and glass identification dataset) is compared.
Abstract: Supervised algorithms depend on the given data for categorizing. In present work, we used both parametric and nonparametric types of classifiers. We intend to compare the performance of four popular machine learning classification algorithms—Naive Bayes, decision trees, logistic regression, and random forest on two popular benchmarked datasets—wine quality dataset and glass identification dataset. To get a wide angle of the performance of these algorithms, we incorporated both binary and multi-class classification which also solved the problem of imbalance in the dataset. In current work, we compare and demonstrate various supervised machine learning classification algorithms on the two well-known datasets. The performance of the algorithms was measured using accuracy, recall, precision, and F1-score. It was observed that nonparametric algorithms like random forest classifier and decision tree classifier bested the parametric algorithms like logistic regression and naive Bayes. Moreover, as the datasets were imbalanced, we figured out which algorithm performs better under what circumstances. In particular, random forest achieved best performance in terms of all considered metrics, with accuracy of 82 and 83% in wine datasets and 79% in glass identification dataset.

1 citations

References
More filters
Proceedings ArticleDOI
23 Mar 2012
TL;DR: This paper provides a concise but all-round analysis on data security and privacy protection issues associated with cloud computing across all stages of data life cycle and describes future research work about dataSecurity and privacy Protection issues in cloud.
Abstract: It is well-known that cloud computing has many potential advantages and many enterprise applications and data are migrating to public or hybrid cloud. But regarding some business-critical applications, the organizations, especially large enterprises, still wouldn't move them to cloud. The market size the cloud computing shared is still far behind the one expected. From the consumers' perspective, cloud computing security concerns, especially data security and privacy protection issues, remain the primary inhibitor for adoption of cloud computing services. This paper provides a concise but all-round analysis on data security and privacy protection issues associated with cloud computing across all stages of data life cycle. Then this paper discusses some current solutions. Finally, this paper describes future research work about data security and privacy protection issues in cloud.

654 citations

Journal ArticleDOI
TL;DR: This article analyzes the privacy risks associated with several current and prominent personalization trends, namely social-based personalization, behavioral profiling, and location-basedpersonalization, and surveys user attitudes towards privacy and personalization.
Abstract: Personalization technologies offer powerful tools for enhancing the user experience in a wide variety of systems, but at the same time raise new privacy concerns. For example, systems that personalize advertisements according to the physical location of the user or according to the user's friends' search history, introduce new privacy risks that may discourage wide adoption of personalization technologies. This article analyzes the privacy risks associated with several current and prominent personalization trends, namely social-based personalization, behavioral profiling, and location-based personalization. We survey user attitudes towards privacy and personalization, as well as technologies that can help reduce privacy risks. We conclude with a discussion that frames risks and technical solutions in the intersection between personalization and privacy, as well as areas for further investigation. This frameworks can help designers and researchers to contextualize privacy challenges of solutions when designing personalization systems.

204 citations

Posted Content
TL;DR: This work analyzes two of Facebooks more recent features, Applications and News Feed, from the perspective enabled by Helen Nissenbaum’s treatment of privacy as “contextual integrity,” finding that many of the privacy issues on Facebook are primarily design issues, which could be ameliorated by an interface that made the flows of information more transparent to users.
Abstract: Social networking sites like Facebook are rapidly gaining in popularity. At the same time, they seem to present significant privacy issues for their users. We analyze two of Facebooks’s more recent features, Application and News Feed, from the perspective enabled by Helen Nissenbaum’s treatment of privacy as “contextual integrity.” Offline, privacy is mediated by highly granular social contexts. Online contexts, including social networking sites, lack much of this granularity. These contextual gaps are at the root of many of the sites’ privacy issues. Application, which nearly invisibly shares not just a users’, but a user’s friends’ information with third parties, clearly violates standard norms of information flow. News Feed is a more complex case, because it involves not just questions of privacy, but also of program interface and of the meaning of “friendship” online. In both cases, many of the privacy issues on Facebook are primarily design issues, which could be ameliorated by an interface that made the flows of information more transparent to users.

143 citations

Journal ArticleDOI
TL;DR: In this paper, the authors analyze two of Facebook's more recent features, Applications and News Feed, from the perspective enabled by Helen Nissenbaum's treatment of privacy as "contextual integrity".
Abstract: Social networking sites like Facebook are rapidly gaining in popularity At the same time, they seem to present significant privacy issues for their users We analyze two of Facebooks's more recent features, Applications and News Feed, from the perspective enabled by Helen Nissenbaum's treatment of privacy as "contextual integrity" Offline, privacy is mediated by highly granular social contexts Online contexts, including social networking sites, lack much of this granularity These contextual gaps are at the root of many of the sites' privacy issues Applications, which nearly invisibly shares not just a users', but a user's friends' information with third parties, clearly violates standard norms of information flow News Feed is a more complex case, because it involves not just questions of privacy, but also of program interface and of the meaning of "friendship" online In both cases, many of the privacy issues on Facebook are primarily design issues, which could be ameliorated by an interface that made the flows of information more transparent to users

120 citations

Book ChapterDOI
Judy Kay1
21 Jun 2006
TL;DR: The paper illustrates PLUS in terms of its existing, implemented elements as well as some examples of applications built upon this approach, a vision of Pervasive Lifelong User-models that are Scrutable.
Abstract: Beginning with the motivations for scrutability, this paper introduces PLUS, a vision of Pervasive Lifelong User-models that are Scrutable. The foundation for PLUS is the Accretion/Resolution representation for active user models that can drive adaptive hypermedia, with support for scrutability. The paper illustrates PLUS in terms of its existing, implemented elements as well as some examples of applications built upon this approach. The concluding section is a research agenda for essential elements of this PLUS vision.

103 citations