Protecting Sensory Data against Sensitive Inferences

By Mohammad Malekzadeh, Richard G. Clegg, Andrea Cavallaro, Hamed Haddadi. 2018

205 citations recorded by the source corpus.

There is growing concern about how personal data are used when users grant applications direct access to the sensors of their mobile devices. In fact, high resolution temporal data generated by motion sensors reflect directly the activities of a user and indirectly physical and demographic attributes. In this paper, we propose a feature learning architecture for mobile devices that provides flexible and negotiable privacy-preserving sensor data transmission by appropriately transforming raw sensor data. The objective is to move from the current binary setting of granting or not permission to an application, toward a model that allows users to grant each application permission over a limited range of inferences according to the provided services. The internal structure of each component of the proposed architecture can be flexibly changed and the trade-off between privacy and utility can be negotiated between the constraints of the user and the underlying application. We validated the proposed architecture in an activity recognition application using two real-world datasets, with the objective of recognizing an activity without disclosing gender as an example of private information. Results show that the proposed framework maintains the usefulness of the transformed data for activity recognition, with an average loss of only around three percentage points, while reducing the possibility of gender classification to around 50%, the target random guess, from more than 90% when using raw sensor data. We also present and distribute MotionSense, a new dataset for activity and attribute recognition collected from motion sensors.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing

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 Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

Privacy in Deep Learning: A Survey (2020, background): “Privacy-preserving schemes that rely on information-theoretic approaches usually assume a nonsensitive task, the task that the service is supposed to execute and try to degrade any excessive information in the input data that is not needed for the main inference task [142, 145, 143, 29, 31, 146].”
Olympus: Sensor Privacy through Utility Aware Obfuscation (2018, unknown): “Our work is closely related to the recently proposed obfuscation techniques that formulate the obfuscation problem as a minimax optimization [15, 18, 32, 37, 39, 41].”
PrivEdge: From Local to Distributed Private Training and Prediction (2020, background): “To preserve privacy, local data anonymisation [7], [8] or data encryption [14] can be performed on the user side, prior to transmission to the service provider.”
Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances (2021, methodology): “introduces a framework called Guardian-Estimator-Neutralizer (GEN) that attempts to recognize activities while preserving gender privacy [180].”
Deep Learning for Sensor-based Human Activity Recognition (2020, background): “rocess. For example, Iwasawa et al. [65] proposed to integrate an adversarial loss with the standard activity classification loss to minimize the user identification accuracy. The authors of [92] and [91] also adopted the similar idea to prevent privacy leakage. Their experiment results show an effe”
A Hybrid Deep Learning Architecture for Privacy-Preserving Mobile Analytics (2017, methodology): “Data Set: We used the MotionSense data set [28] for all the stages of Siamese fine-tuning, predictive accuracy assessment, and transfer learning.”
Multi-task Self-Supervised Learning for Human Activity Detection (2019, background): “e MotionSense dataset [40] comprises an accelerometer, gyroscope, and altitude data from 24 participants of varying age, gender, weight, and height.”
Privacy and Utility Preserving Sensor-Data Transformations (2019, methodology): “MotionSense [43] is collected with a smart-phone kept in the users’ front pocket.”