Privacy-Aware Human Mobility Prediction via Adversarial Networks

  title={Privacy-Aware Human Mobility Prediction via Adversarial Networks},
  author={Yuting Zhan and Alex Kyllo and Afra Jahanbakhsh Mashhadi and Hamed Haddadi},
  journal={2022 2nd International Workshop on Cyber-Physical-Human System Design and Implementation (CPHS)},
  • Yuting ZhanAlex Kyllo H. Haddadi
  • Published 19 January 2022
  • Computer Science
  • 2022 2nd International Workshop on Cyber-Physical-Human System Design and Implementation (CPHS)
As various mobile devices and location-based ser-vices are increasingly developed in different smart city scenarios and applications, many unexpected privacy leakages have arisen due to geolocated data collection and sharing. While these geolocated data could provide a rich understanding of human mobility patterns and address various societal research questions, privacy concerns for users' sensitive information have limited their utilization. In this paper, we design and implement a novel LSTM… 

Figures and Tables from this paper



LSTM-TrajGAN: A Deep Learning Approach to Trajectory Privacy Protection

This research proposes a novel LSTM-TrajGAN approach, which is an end-to-end deep learning model to generate privacy-preserving synthetic trajectory data for data sharing and publication, and designs a loss metric function TrajLoss to measure the trajectory similarity losses for model training and optimization.

User Mobility Synthesis based on Generative Adversarial Networks: A Survey

This paper reviews and summarizes recently proposed user mobility synthesis schemes based on generative adversarial networks that have been one of the most leading deep learning technologies for the last few years.

A Non-Parametric Generative Model for Human Trajectories

A novel non-parametric generative model for location trajectories that tries to capture the statistical features of human mobility, in contrast with existing models that generate trajectories in a sequential manner is proposed and evaluated.

Privacy Adversarial Network

The privacy adversarial network (PAN) is a novel deep model with the new training algorithm, that can automatically learn representations from the raw data that achieves better utility and better privacy at the same time.

PRIVA'MOV: Analysing Human Mobility Through Multi-Sensor Datasets

This paper presents the PRIVA'MOV dataset, a novel dataset collected in the city of Lyon, France on which user mobility has been collected using multiple sensors, and analyses the uniqueness of human mobility by considering the various sensors.

Protecting Locations with Differential Privacy under Temporal Correlations

A new definition, "Ξ΄-location set" based differential privacy, is proposed, to account for the temporal correlations in location data and a planar isotropic mechanism (PIM) for location perturbation, which is the first mechanism achieving the lower bound of differential privacy.

Protecting Sensitive Attributes via Generative Adversarial Networks

This paper uses deep neural networks and generative adversarial networks to create privacy-preserving perturbations and proposes a generic framework that removes the knowledge useful for inferring sensitive information, but preserves the knowledge relevant to a given target application.

Privacy and Utility Preserving Sensor-Data Transformations

A Variational Autoencoder Based Generative Model of Urban Human Mobility

  • Dou HuangXuan Song Yugo Kato
  • Computer Science
    2019 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR)
  • 2019
Experimental results demonstrate that the SVAE model can efficiently capture the salient features of human mobility data and generate more reasonable trajectories.

A Survey on Deep Learning for Human Mobility

This survey provides a taxonomy of mobility tasks, a discussion on the challenges related to each task and how deep learning may overcome the limitations of traditional models, a description of the most relevant solutions to the mobility tasks described above, and the relevant challenges for the future.