SwipeVLock: A supervised unlocking mechanism based on swipe behavior on smartphones

Wenjuan LI, Jiao TAN, Weizhi MENG, Yu WANG, Jing LI

Research output: Chapter in Book/Report/Conference proceedingChapters

11 Citations (Scopus)

Abstract

Smartphones have become a necessity in people’s daily lives, and changed the way of communication at any time and place. Nowadays, mobile devices especially smartphones have to store and process a large amount of sensitive information, i.e., from personal to financial and professional data. For this reason, there is an increasing need to protect the devices from unauthorized access. In comparison with the traditional textual password, behavioral authentication can verify current users in a continuous way, which can complement the existing authentication mechanisms. With the advanced capability provided by current smartphones, users can perform various touch actions to interact with their devices. In this work, we focus on swipe behavior and aim to design a machine learning-based unlock scheme called SwipeVLock, which verifies users based on their way of swiping the phone screen with a background image. In the evaluation, we measure several typical supervised learning algorithms and conduct a user study with 30 participants. Our experimental results indicate that participants could perform well with SwipeVLock, i.e., with a success rate of 98% in the best case. Copyright © 2019 Springer Nature Switzerland AG.

Original languageEnglish
Title of host publicationMachine learning for cyber security: Second International Conference, ML4CS 2019, Xi’an, China, September 19-21, 2019, proceedings
EditorsXiaofeng CHEN, Xinyi HUANG, Jun ZHANG
Place of PublicationCham
PublisherSpringer
Pages140-153
ISBN (Electronic)9783030306199
ISBN (Print)9783030306182
DOIs
Publication statusPublished - 2019

Citation

Li, W., Tan, J., Meng, W., Wang, Y., & Li, J. (2019). SwipeVLock: A supervised unlocking mechanism based on swipe behavior on smartphones. In X. Chen, X. Huang, & J. Zhang (Eds.), Machine learning for cyber security: Second International Conference, ML4CS 2019, Xi’an, China, September 19-21, 2019, proceedings (pp. 140-153). Springer. https://doi.org/10.1007/978-3-030-30619-9_11

Keywords

  • User authentication
  • Behavioral biometric
  • Swipe behavior
  • Smartphone security
  • Touch action

Fingerprint

Dive into the research topics of 'SwipeVLock: A supervised unlocking mechanism based on swipe behavior on smartphones'. Together they form a unique fingerprint.