Title :
An obfuscation framework for controlling value of information during sharing
Author :
Chakraborty, Supriyo ; Raghavan, Kasturi Rangan ; Srivastava, Mani B. ; Bisdikian, Chatschik ; Kaplan, Lance M.
Author_Institution :
Univ. of California, Los Angeles, CA, USA
Abstract :
Sensory information is characterized by its inherent quality and context-specific value. It is thus natural that the information provider would want to exercise control over the information shared based on her perception of the risk of possible misuse due to sharing and also depending on the consumer requirements. To attain this utility vs. risk trade-off, information is subjected to varying but deliberate quality modifying transformations which we term as obfuscation. In this paper, treating privacy as the primary motivation for information control, we highlight initial considerations of using feature sharing as an obfuscation mechanism to control the inferences possible from shared sensory data. We provide results from an activity tracking scenario to illustrate the use of feature selection in identifying the various trade-off points.
Keywords :
data privacy; inference mechanisms; activity tracking scenario; consumer requirements; context specific value; data privacy; feature selection; feature sharing; information control; information provider; information sharing; obfuscation framework; quality modifying transformations; sensory information; shared sensory data; Accuracy; Data privacy; Feature extraction; Inference algorithms; Mutual information; Privacy; Feature Sharing; Mutual Information; Privacy; Utility; Value of Information;
Conference_Titel :
Statistical Signal Processing Workshop (SSP), 2012 IEEE
Conference_Location :
Ann Arbor, MI
Print_ISBN :
978-1-4673-0182-4
Electronic_ISBN :
pending
DOI :
10.1109/SSP.2012.6319647