Protecting Sensory Data against Sensitive Inferences

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.

[1]  Yoshua Bengio,et al.  Extracting and composing robust features with denoising autoencoders , 2008, ICML '08.

[2]  Zhiwei Steven Wu,et al.  Privacy-Preserving Generative Deep Neural Networks Support Clinical Data Sharing , 2017, bioRxiv.

[3]  SalvadorStan,et al.  Toward accurate dynamic time warping in linear time and space , 2007 .

[4]  Eamonn J. Keogh,et al.  The great time series classification bake off: a review and experimental evaluation of recent algorithmic advances , 2016, Data Mining and Knowledge Discovery.

[5]  Jimeng Sun,et al.  Generating Multi-label Discrete Patient Records using Generative Adversarial Networks , 2017, MLHC.

[6]  Jimeng Sun,et al.  Generating Multi-label Discrete Electronic Health Records using Generative Adversarial Networks , 2017, ArXiv.

[7]  Cynthia Dwork,et al.  Differential Privacy: A Survey of Results , 2008, TAMC.

[8]  Manolis Tsiknakis,et al.  The MobiAct Dataset: Recognition of Activities of Daily Living using Smartphones , 2016, ICT4AgeingWell.

[9]  Ye Wang,et al.  Privacy-Preserving Adversarial Networks , 2017, 2019 57th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[10]  Mohammad Malekzadeh,et al.  Replacement AutoEncoder: A Privacy-Preserving Algorithm for Sensory Data Analysis , 2017, 2018 IEEE/ACM Third International Conference on Internet-of-Things Design and Implementation (IoTDI).

[11]  Hamed Haddadi,et al.  Poster: SensingKit: a multi-platform mobile sensing framework for large-scale experiments , 2014, MobiCom.

[12]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[13]  Gunnar Rätsch,et al.  Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs , 2017, ArXiv.

[14]  Casey S. Greene,et al.  Privacy-preserving generative deep neural networks support clinical data sharing , 2017 .

[15]  Hamed Haddadi,et al.  Personal Data: Thinking Inside the Box , 2015, Aarhus Conference on Critical Alternatives.

[16]  Mani B. Srivastava,et al.  mSieve: differential behavioral privacy in time series of mobile sensor data , 2016, UbiComp.

[17]  Ram Rajagopal,et al.  Context-Aware Generative Adversarial Privacy , 2017, Entropy.

[18]  Xiaoli Li,et al.  Deep Convolutional Neural Networks on Multichannel Time Series for Human Activity Recognition , 2015, IJCAI.

[19]  Philip Chan,et al.  Toward accurate dynamic time warping in linear time and space , 2007, Intell. Data Anal..