02139nas a2200445 4500008004100000245007500041210006900116260000800185520088000193653001901073653001201092653001501104653002201119653001601141653001701157653002501174653002501199653002101224653002301245653001701268653003101285653002701316653001401343653001201357653002101369653001301390653002501403653001201428653002201440653002401462653002201486653001601508653001701524653003101541653002901572100002301601700001701624700001501641856003701656 2015 eng d00aRandom anonymization of mobile sensor data: Modified Android framework0 aRandom anonymization of mobile sensor data Modified Android fram cMay3 a
With the increasing ability to accurately classify activities of mobile users from what was once viewed as innocuous mobile sensor data, the risk of users compromising their privacy has risen exponentially. Currently, mobile owners cannot control how various applications handle the privacy of their sensor data, or even determine if a service provider is adversarial or trustworthy. To address these privacy concerns, third party applications have been designed to allow mobile users to have control over the data that is sent to service providers. However, these applications require users to set flags and parameters that place restrictions on the anonymized or real sensor data that is sent to the requestor. Therefore, in this paper, we introduce a new framework, RANDSOM, that moves the decision-making from the application level to the operating system level.
10aAccelerometers10aAndroid10aanonymized10aapplication level10aData models10adata privacy10aHidden Markov models10aMobile communication10amobile computing10amobile sensor data10amobile users10amodified Android framework10aoperating system level10apervasive10aPrivacy10aprivacy concerns10aprovider10arandom anonymization10aRANDSOM10aRANDSOM framework10asensor data privacy10aservice providers10asmart phone10asmart phones10atelecommunication security10athird party applications1 aClaiborne, Cynthia1 aNcube, Cathy1 aDantu, Ram uhttps://nsl.cse.unt.edu/node/158