DEEProtect: Enabling Inference-based Access Control on Mobile Sensing Applications

By Changchang Liu, Supriyo Chakraborty, Prateek Mittal. 2017

27 citations recorded by the source corpus.

Personal sensory data is used by context-aware mobile applications to provide utility. However, the same data can also be used by an adversary to make sensitive inferences about a user thereby violating her privacy. We present DEEProtect, a framework that enables a novel form of inference control, in which mobile apps with access to sensor data are limited (provably) in their ability to make inferences about user's sensitive data and behavior. DEEProtect adopts a two-layered privacy strategy. First, it leverages novel autoencoder techniques to perform data minimization and limits the amount of information being shared; the learning network is used to derive a compact representation of sensor data consisting only of features relevant to authorized utility-providing inferences. Second, DEEProtect obfuscates the previously learnt features, thereby providing an additional layer of protection against sensitive inferences. Our framework supports both conventional as well as a novel relaxed notion of local differential privacy that enhances utility. Through theoretical analysis and extensive experiments using real-world datasets, we demonstrate that when compared to existing approaches DEEProtect provides provable privacy guarantees with up to 8x improvement in utility. Finally, DEEProtect shares obfuscated but raw sensor data reconstructed from the perturbed features, thus requiring no changes to the existing app interfaces.

Subfields: Artificial Intelligence, Computer Science Applications, Sociology and Political Science

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Science Applications

In Sociology and Political Science

Citations in the corpus

Collecting and Analyzing Multidimensional Data with Local Differential Privacy (2019, background): “Also, LDP has been considered in several applications including the collection of indoor positioning data [26], inference control on mobile sensing [28], and the publication of crowdsourced data [34].”
Learning Generative Adversarial RePresentations (GAP) under Fairness and Censoring Constraints (2019, methodology): “DP-based obfuscators for data publishing have been considered in (Hamm, 2016; Liu et al., 2017).”
Deep Private-Feature Extraction (2018, methodology): “The privacy challenge in dealing with cloud server is also discussed by [35] and [36] using accelerometer sensor’s data.”
Generative Adversarial Privacy: A Data-Driven Approach to Information-Theoretic Privacy (2018, methodology): “DP-based obfuscators for data publishing have been considered in [13, 21].”
Mobile sensor data anonymization (2018, background): “Moreover, a latent representation can be learned that removes some meaningful patterns from the data to reduce the possibility of inferring sensitive information [9, 16].”
Context-Aware Generative Adversarial Privacy (2017, methodology): “The approach in [54] relies on using deep auto-encoders to determine the relevant feature space to add di erentially private noise to, eliminating the need to add noise to the original data.”