Chapter

Secure Data Management

Volume 4165 of the series Lecture Notes in Computer Science pp 30-47

Temporal Context Lie Detection and Generation

  • Xiangdong AnAffiliated withFaculty of Computer Science, Dalhousie UniversityFinance and Management Science Department, Saint Mary’s University
  • , Dawn JutlaAffiliated withFinance and Management Science Department, Saint Mary’s University
  • , Nick CerconeAffiliated withFaculty of Computer Science, Dalhousie University

* Final gross prices may vary according to local VAT.

Get Access

Abstract

In pervasive (ubiquitous) environments, context-aware agents are used to obtain, understand, and share local contexts with each other so that all resources in the environments could be integrated seamlessly. Context exchanging should be made privacy-conscious, which is generally controlled by users’ privacy preferences. Besides who has rights to get what true information about him, a user’s privacy preference could also designate who should be given obfuscated information. By obfuscation, people could present their private information in a coarser granularity, or simply in a falsified manner, depending on the specific situations. Nevertheless, obfuscation cannot be done randomly because by reasoning the receiver could know the information has been obfuscated. An obfuscated context can not only be inferred from its dependencies with other existing contexts, but could also be derived from its dependencies with the vanished ones. In this paper, we present a dynamic Bayesian network (DBN)-based method to reason about the obfuscated contexts in pervasive environments, where the impacts of the vanished historical contexts are properly evaluated. On the one hand, it can be used to detect obfuscations, and may further find the true information; on the other hand, it can help reasonably obfuscate information.

Keywords

Privacy management context inference inference control obfuscation pervasive computing dynamic Bayesian networks uncertain reasoning