Preserving Privacy in Personalized Models for Distributed Mobile Services

01/14/2021
by   Akanksha Atrey, et al.
0

The ubiquity of mobile devices has led to the proliferation of mobile services that provide personalized and context-aware content to their users. Modern mobile services are distributed between end-devices, such as smartphones, and remote servers that reside in the cloud. Such services thrive on their ability to predict future contexts to pre-fetch content of make context-specific recommendations. An increasingly common method to predict future contexts, such as location, is via machine learning (ML) models. Recent work in context prediction has focused on ML model personalization where a personalized model is learned for each individual user in order to tailor predictions or recommendations to a user's mobile behavior. While the use of personalized models increases efficacy of the mobile service, we argue that it increases privacy risk since a personalized model encodes contextual behavior unique to each user. To demonstrate these privacy risks, we present several attribute inference-based privacy attacks and show that such attacks can leak privacy with up to 78 privacy-preserving personalization system for context-aware mobile services that leverages both device and cloud resources to personalize ML models while minimizing the risk of privacy leakage for users. We evaluate Pelican using real world traces for location-aware mobile services and show that Pelican can substantially reduce privacy leakage by up to 75

READ FULL TEXT

page 1

page 7

page 9

research
08/02/2018

The Privacy Exposure Problem in Mobile Location-based Services

Mobile location-based services (LBSs) empowered by mobile crowdsourcing ...
research
12/12/2018

Analysis of Location Data Leakage in the Internet Traffic of Android-based Mobile Devices

In recent years we have witnessed a shift towards personalized, context-...
research
10/23/2017

Interpretable Machine Learning for Privacy-Preserving Pervasive Systems

The presence of pervasive systems in our everyday lives and the interact...
research
04/21/2019

HCFContext: Smartphone Context Inference via Sequential History-based Collaborative Filtering

Mobile context determination is an important step for many context aware...
research
02/03/2022

VindiCo: Privacy Safeguard Against Adaptation Based Spyware in Human-in-the-Loop IoT

Personalized IoT adapts their behavior based on contextual information, ...
research
10/05/2016

The Predictive Context Tree: Predicting Contexts and Interactions

With a large proportion of people carrying location-aware smartphones, w...
research
07/15/2019

Utility-aware and privacy-preserving mobile query services

Location-based queries enable fundamental services for mobile road netwo...

Please sign up or login with your details

Forgot password? Click here to reset