Mobile Sensor Data Anonymization
arXiv:1810.11546 · doi:10.1145/3302505.3310068
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%.
10 pages
References in corpus (1)
Cited by in corpus (27)
- Sensing, Computing, and Communication for Energy Harvesting IoTs: A Survey
- Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities
- Privacy in Deep Learning: A Survey
- Zeno: An Interactive Framework for Behavioral Evaluation of Machine Learning
- DeepObfuscator: Obfuscating Intermediate Representations with Privacy-Preserving Adversarial Learning on Smartphones
- Socially Responsible AI Algorithms: Issues, Purposes, and Challenges
- Privacy-preserving Voice Analysis via Disentangled Representations
- QUOTIENT: Two-Party Secure Neural Network Training and Prediction
- Evaluating Large Language Models as Virtual Annotators for Time-series Physical Sensing Data
- DANA: Dimension-Adaptive Neural Architecture for Multivariate Sensor Data
- Embedding and learning with signatures
- PriMask: Cascadable and Collusion-Resilient Data Masking for Mobile Cloud Inference
- FreRA: A Frequency-Refined Augmentation for Contrastive Learning on Time Series Classification
- A systematic review of smartphone-based human activity recognition for health research
- Reliable and Trustworthy Machine Learning for Health Using Dataset Shift Detection
- Privacy Assessment of Federated Learning using Private Personalized Layers
- Finding Dory in the Crowd: Detecting Social Interactions using Multi-Modal Mobile Sensing
- Blinder: End-to-end Privacy Protection in Sensing Systems via Personalized Federated Learning
- Anonymizing Sensor Data on the Edge: A Representation Learning and Transformation Approach
- EarDA: Towards Accurate and Data-Efficient Earable Activity Sensing
- On Neural Inertial Classification Networks for Pedestrian Activity Recognition
- Self-Supervised Learning and Opportunistic Inference for Continuous Monitoring of Freezing of Gait in Parkinson's Disease
- Anonymization for Skeleton Action Recognition
- Saga: Capturing Multi-granularity Semantics from Massive Unlabelled IMU Data for User Perception
- Dynamic Black-box Backdoor Attacks on IoT Sensory Data
- Emotion Filtering at the Edge
- Experience Paper: Adopting Activity Recognition in On-demand Food Delivery Business