Risk Assessment of Private Information Inference for Motion Sensor Embedded IoT Devices

Yan Huang, Xin Guan, Hongyang Chen, Yi Liang, Shanshan Yuan, Tomoaki Ohtsuki

Research output: Contribution to journalArticle

Abstract

In the era of advanced computer intelligence, Internet of Things (IoT) provides fantastic services to users. However, users are suffering a severe risk of private information inference, which is caused by the leakage of motion sensory data from IoT devices. Existing works of risk assessment of motion sensor based private information inference underestimates the risk because they ignore the possibility of using advanced Computational Intelligence techniques and the variety of languages with different input methods. In this paper, we assess the risk of motion sensor based private information inference by considering the variety of languages with different input methods, advanced Computational Intelligence techniques, and reinforcement learning of personal usage habits. We collect data from real users and run simulations to provide an authentic and up-to-date risk assessment. Based on the simulation result, we discuss the risky usage actions and possible defense strategies for the Internet of Things users.

Original languageEnglish
Article number8887225
Pages (from-to)265-275
Number of pages11
JournalIEEE Transactions on Emerging Topics in Computational Intelligence
Volume4
Issue number3
DOIs
Publication statusPublished - 2020 Jun

Keywords

  • computer intelligence
  • embedded sensors
  • Internet of Things
  • Privacy
  • private information inference

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Computational Mathematics
  • Control and Optimization

Fingerprint Dive into the research topics of 'Risk Assessment of Private Information Inference for Motion Sensor Embedded IoT Devices'. Together they form a unique fingerprint.

  • Cite this