Mobile sensor data anonymization

Abstract

Motion sensors such as accelerometers and gyroscopes measure the instant acceleration and rotation of a device, in three dimensions. Raw data streams from motion sensors embedded in portable and wearable devices may reveal private information about users without their awareness. For example, motion data might disclose the weight or gender of a user, or enable their re-identification. To address this problem, we propose an on-device transformation of sensor data to be shared for specific applications, such as monitoring selected daily activities, without revealing information that enables user identification. We formulate the anonymization problem using an information-theoretic approach and propose a new multi-objective loss function for training deep autoencoders. This loss function helps minimizing user-identity information as well as data distortion to preserve the application-specific utility. The training process regulates the encoder to disregard user-identifiable patterns and tunes the decoder to shape the output independently of users in the training set. The trained autoencoder can be deployed on a mobile or wearable device to anonymize sensor data even for users who are not included in the training dataset. Data from 24 users transformed by the proposed anonymizing autoencoder lead to a promising trade-off between utility and privacy, with an accuracy for activity recognition above 92% and an accuracy for user identification below 7%.

Smartphone Location Recognition: A Deep Learning-Based Approach

“…The fifth dataset [34] was used to examine a new approach to a multi-objective loss function for training deep autoencoders for HAR applications. The dataset was recorded by 24 people (10 women and 14 men) using a smartphone in their pocket.…”

Privacy and utility preserving sensor-data transformations

“…The goal of training AAE is to minimize the privacy loss by minimizing the amount of information leakage from U to X . Hence, we use adversarial training to approximate the mutual information by estimating the posterior distribution of the sensitive data given the released data [38].…”

“…To simplify the process of encoding data into a lower-dimensional representation and then decoding it to the original dimension with convolutional filters, we set W to be a power of 2. The larger W, the lower the possibility of taking advantage of the correlation among the successive windows by adversaries [38]. But larger window sizes increase the delay for real-time apps.…”

Motion Type Verification Studies Using Accelerometer Sensor Data With Local Mean Decomposition

“…Çalışmamızda kullanılan veriler daha önce kontrollü bir şekilde kaydedilip sonra konu ile ilgili akademik çalışmaların yapıldığı test edilmiş güvenilir bir veridir [1]. 3 eksen ivme ölçer verisi kullanılmıştır.…”

“…Çalışmamızda ivme ölçer sensörü kaydına ilişkin veriler kullanılmıştır. Veriler M. Malekzadeh ve arkadaşlarının [1] yaptığı çalışma neticesinde çeşitli boy, kilo, yaş ve cinsiyet bilgisine sahip 24 kişiden alınmıştır. Çalışmamızda ise 5 erkek ve 5 kadın bireye ait ivme ölçer verileri kullanılmıştır.…”