User-Controllable Learning of Location Privacy Policies With Gaussian Mixture Models

@article{Cranshaw2011UserControllableLO,
  title={User-Controllable Learning of Location Privacy Policies With Gaussian Mixture Models},
  author={Justin Cranshaw and Jonathan Mugan and Norman M. Sadeh},
  journal={Proceedings of the AAAI Conference on Artificial Intelligence},
  year={2011}
}
With smart-phones becoming increasingly commonplace, there has been a subsequent surge in applications that continuously track the location of users. However, serious privacy concerns arise as people start to widely adopt these applications. Users will need to maintain policies to determine under which circumstances to share their location. Specifying these policies however, is a cumbersome task, suggesting that machine learning might be helpful. In this paper, we present a user… 

Figures and Tables from this paper

Crowdsourcing privacy preferences in context-aware applications
  • Eran Toch
  • Computer Science
    Personal and Ubiquitous Computing
  • 2012
TLDR
This work presents Super-Ego, a crowdsourcing framework for privacy management of location information in ubiquitous environment, and studies how crowdsourcing can be used to predict the user’s privacy preferences for different location on the basis of the general user population.
Recommending privacy preferences in location-sharing services
TLDR
This thesis investigates the feasibility of using recommender systems to help people protect their location privacy and finds that user-based collaborative filtering can accurately recommend locationprivacy preferences and outperform the state-of-the-art when training data are insufficient.
The Persuasive Effect of Privacy Recommendations for Location Sharing Services
TLDR
Two studies explore ways to help users with fine-grained location-sharing decisions and show that although users differ wildly in their preferred sharing actions for any given scenario, users’ evaluation of the activity described in the scenario is a good predictor of the sharing action they choose.
Understanding and capturing people's mobile app privacy preferences
TLDR
This thesis combines static code analysis, crowdsourcing and machine learning techniques to elicit people's mobile app privacy preferences, and introduces a crowdsourcing methodology to collect people's privacy preferences when it comes to granting permissions to mobile apps for different purposes.
SmarPer: Context-Aware and Automatic Runtime-Permissions for Mobile Devices
TLDR
This work is the first to show, using a large dataset of real in situ permission decisions, that it is possible to learn users' unique decision patterns at runtime using contextual information while supporting data obfuscation, this is an important step towards automating the management of permissions in smartphones.
Follow My Recommendations: A Personalized Privacy Assistant for Mobile App Permissions
TLDR
A field study in which a Personalized Privacy Assistant (PPA) was implemented and evaluated with participants using their own Android devices, and it is found that 78.7% of the recommendations made by the PPA were adopted by users.
Privacy Challenges in Smart Devices
TLDR
This proposal examines existing issues with smartphone privacy-protection mechanisms, and takes a look at machine learning techniques which could be used to improve these mechanisms, as well as an example of such an application: using machineLearning techniques to learn user location privacy policies.
User-Tailored Privacy
TLDR
This chapter covers the concept of tailoring the privacy of an information system to each individual user, and discusses practical problems that may arise when collecting data to determine a user's privacy preferences, techniques to model these preferences, and a number of adaptation strategies that can be used to tailor the system’s privacy practices, settings, or interfaces to the user's modeled preferences.
The Persuasive Effect of Privacy Recommendations
Several researchers have recently suggested that in order to avoid privacy problems, location-sharing services should provide finer-grained methods of location-sharing. This may however turn each
Privacy Dynamics: Learning Privacy Norms for Social Software
  • G. Çalikli, Mark Law, B. Nuseibeh
  • Computer Science
    2016 IEEE/ACM 11th International Symposium on Software Engineering for Adaptive and Self-Managing Systems (SEAMS)
  • 2016
TLDR
An adaptive architecture that learns privacy norms for dierent audience groups based on users' sharing behaviours, underpinned by a formal model inspired by social identity theory, a social psychology framework for analysing group processes and intergroup re- lations.
...
...

References

SHOWING 1-10 OF 15 REFERENCES
User-controllable learning of security and privacy policies
TLDR
Results obtained using a neighborhood search implementation of this approach are presented in the context of data derived from the deployment of a friend finder application, where users can share their locations with others, subject to privacy policies they refine over time.
Understanding and capturing people’s privacy policies in a mobile social networking application
TLDR
This article reports on the work on PeopleFinder, an application that enables cell phone and laptop users to selectively share their locations with others, and explores technologies that empower users to more effectively and efficiently specify their privacy preferences.
Privacy wizards for social networking sites
TLDR
A template for the design of a social networking privacy wizard based on an active learning paradigm called uncertainty sampling, which is able to recommend high-accuracy privacy settings using less user input than existing policy-specification tools.
Capturing location-privacy preferences: quantifying accuracy and user-burden tradeoffs
TLDR
One practical implication of the results is that today’s location-sharing applications may have failed to gain much traction due to their limited privacy settings, as they appear to be ineffective at capturing the preferences revealed by the study.
Location privacy in pervasive computing
TLDR
This chapter focuses on the privacy aspects of using location information in location-based services (LBSs), which are services that take the current position of the user into consideration when performing their tasks.
Learning travel recommendations from user-generated GPS traces
TLDR
This article performs two types of travel recommendations by mining multiple users' GPS traces, including a generic one that recommends a user with top interesting locations and travel sequences in a given geospatial region and a personalized recommendation that provides an individual with locations matching her travel preferences.
Location-Sharing Technologies: Privacy Risks and Controls
TLDR
It is found that while location-sharing applications do not offer their users a diverse set of rules to control the disclosure of their location, they offer a modicum of privacy.
MCLUST Version 3 for R: Normal Mixture Modeling and Model-Based Clustering †
TLDR
A number of features of the software have been changed in this version, and the functionality has been expanded to include regularization for normal mixture models via a Bayesian prior.
Improving user-interface dependability through mitigation of human error
Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions
This paper presents an overview of the field of recommender systems and describes the current generation of recommendation methods that are usually classified into the following three main
...
...