Behavioral Privacy

Patricia Guerra Balboa, Simon Hanisch, Matin Fallahi, Alex Miranda Pascual

Here you can access the studies of the research group 

Anonymizing humans in motion  Researcher Simon Hanisch (PhD Student)
Motivation
  • How can we use human motion data without creating a privacy problem for the recorded person?
  • What makes human motion unique and what is important for the recognition of individuals?
Use-case
  • Anonymization for human motion data publishing
  • Removing sensitive attributes (age, gender, etc.) from human motion data
Methods
  • User-studies to collect suitable biometric data for anonymization
  • Machine learning to build recognition techniques against which we can evaluate
  • Systematic feature analysis to understand the recognition process
  • Anonymization technique development
Future
  • Development of a better methodology for evaluating biometric anonymization performance
  • Anonymization techniques for human gait
  • Anonymization techniques for freehand gesture controls

 

Security and privacy of behavioral data-driven applications Researcher Matin Fallahi (PhD Student)
Motivation
  • Nowadays everybody has to be authenticated several times per day! Even you :)
  • Most of the time we have to deal with passwords and their pitfalls. Can we do better?
Use-case
  • Could be everywhere, however, our current focus is on the Industry 4.0! (The next generation of factories!).
  • We want to enable easy, hands-free authentication for workers.
Methods
  • Using AI on behavioral data to develop novel biometric systems that are secure, usable, and provide  a better level of privacy. (behavioral biometrics like brainwaves, eye gaze, etc.)
Future
  • Next generation of authentication systems.

 

Anonymizing of humans trajectory data Researchers Patricia Guerra Balboa and Alex Miranda Pascual (PhD Students)
Motivation
  • Trajectory data analysis can improve our daily lives helping avoid traffic jams or suggesting us better routes.
  • We need to avoid the privacy leaks of sensitive information of users (address, places they have visited, etc.) that we could find in trajectory databases before using them to desired tasks.
Use-case
  • Anonymization for trajectory data publishing
  • Private learning for trajectory data 
Methods
  • Adaptation of existing differential privacy mechanism and also creation of new ones to the special needs of trajectory data.
  • Definition of new privacy metrics and notions to understand when a trajectory database is actually protected
Future
  • Development privacy mechanism that overcome the limitations of the existing ones when data-correlations exists in the database (as in trajectories)
  • Anonymization for dynamic data

Slides

Anonymizing of humans trajectory data

Security and privacy of behavioral data-driven applications

Anonymizing humans in motion

Silhouette einer Person


Publications on this topic


Tactile computing: Essential building blocks for the Tactile Internet
Aßmann, U.; Baier, C.; Dubslaff, C.; Grzelak, D.; Hanisch, S.; Hartono, A. P. P.; Köpsell, S.; Lin, T.; Strufe, T.
2021. Tactile Internet. Ed.: F. H.P. Fitzek, 293–317, Academic Press. doi:10.1016/B978-0-12-821343-8.00025-3
Security for mobile edge cloud
Hanisch, S.; Osman, A.; Li, T.; Strufe, T.
2020. Computing in Communication Networks. Ed.: F.H.P. Fitzek, 371–385, Academic Press. doi:10.1016/B978-0-12-820488-7.00038-4
Privacy-Protecting Techniques for Behavioral Data: A Survey
Hanisch, S.; Arias-Cabarcos, P.; Parra-Arnau, J.; Strufe, T.
2021. arxiv. doi:10.5445/IR/1000139989