Keystrokes inference attack on android

A comparative evaluation of sensors and their fusion

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Introducing motion sensors into smartphones contributed to a wide range of applications in human-phone interaction, gaming, and many others. However, built-in sensors that detect subtle motion changes (e.g. accelerometers), might also reveal information about taps on touch screens: the main user input mode. Few researchers have already demonstrated the idea of exploiting motion sensors as side-channels into inferring keystrokes. Taken at most as initial explorations, much research is still needed to analyze the practicality of the new threat and examine various aspects of its implementation. One important aspect affecting directly the attack effectiveness is the selection of the right combination of sensors, to supply inference data. Although other aspects also play crucial role (e.g. the features set), we start in this paper by focusing on the comparison of different available sensors, in terms of the inference accuracy. We consider individual sensors shipped on Android phones, and study few options of preprocessing their raw datasets as well as fusing several sensors' readings. Our results indicate an outstanding performance of the gyroscope, and the potential of sensors data fusion. However, it seems that sensors with magnetometer component or the accelerometer alone have less benefit in the context of the adverted attack.

Original languageEnglish
Pages (from-to)117-136
Number of pages20
JournalJournal of ICT Research and Applications
Volume7
Issue number2
DOIs
Publication statusPublished - 2013

Fingerprint

Fusion reactions
Sensors
Accelerometers
Sensor data fusion
Touch screens
Attack
Sensor
Fusion
Inference
Evaluation
Smartphones
Gyroscopes
Magnetometers

Keywords

  • Android
  • Motion sensors
  • Sensor-based attack
  • Side-channel attack
  • Smartphone security
  • Touchscreen taps inference

ASJC Scopus subject areas

  • Computer Science(all)
  • Electrical and Electronic Engineering
  • Information Systems and Management

Cite this

@article{05cece9463a14528a27374eef2e60b43,
title = "Keystrokes inference attack on android: A comparative evaluation of sensors and their fusion",
abstract = "Introducing motion sensors into smartphones contributed to a wide range of applications in human-phone interaction, gaming, and many others. However, built-in sensors that detect subtle motion changes (e.g. accelerometers), might also reveal information about taps on touch screens: the main user input mode. Few researchers have already demonstrated the idea of exploiting motion sensors as side-channels into inferring keystrokes. Taken at most as initial explorations, much research is still needed to analyze the practicality of the new threat and examine various aspects of its implementation. One important aspect affecting directly the attack effectiveness is the selection of the right combination of sensors, to supply inference data. Although other aspects also play crucial role (e.g. the features set), we start in this paper by focusing on the comparison of different available sensors, in terms of the inference accuracy. We consider individual sensors shipped on Android phones, and study few options of preprocessing their raw datasets as well as fusing several sensors' readings. Our results indicate an outstanding performance of the gyroscope, and the potential of sensors data fusion. However, it seems that sensors with magnetometer component or the accelerometer alone have less benefit in the context of the adverted attack.",
keywords = "Android, Motion sensors, Sensor-based attack, Side-channel attack, Smartphone security, Touchscreen taps inference",
author = "Ahmed Al-Haiqi and Mahamod Ismail and Rosdiadee Nordin",
year = "2013",
doi = "10.5614/itbj.ict.res.appl.2013.7.2.2",
language = "English",
volume = "7",
pages = "117--136",
journal = "Journal of ICT Research and Applications",
issn = "2337-5787",
publisher = "Institut Teknologi Bandung (ITB)",
number = "2",

}

TY - JOUR

T1 - Keystrokes inference attack on android

T2 - A comparative evaluation of sensors and their fusion

AU - Al-Haiqi, Ahmed

AU - Ismail, Mahamod

AU - Nordin, Rosdiadee

PY - 2013

Y1 - 2013

N2 - Introducing motion sensors into smartphones contributed to a wide range of applications in human-phone interaction, gaming, and many others. However, built-in sensors that detect subtle motion changes (e.g. accelerometers), might also reveal information about taps on touch screens: the main user input mode. Few researchers have already demonstrated the idea of exploiting motion sensors as side-channels into inferring keystrokes. Taken at most as initial explorations, much research is still needed to analyze the practicality of the new threat and examine various aspects of its implementation. One important aspect affecting directly the attack effectiveness is the selection of the right combination of sensors, to supply inference data. Although other aspects also play crucial role (e.g. the features set), we start in this paper by focusing on the comparison of different available sensors, in terms of the inference accuracy. We consider individual sensors shipped on Android phones, and study few options of preprocessing their raw datasets as well as fusing several sensors' readings. Our results indicate an outstanding performance of the gyroscope, and the potential of sensors data fusion. However, it seems that sensors with magnetometer component or the accelerometer alone have less benefit in the context of the adverted attack.

AB - Introducing motion sensors into smartphones contributed to a wide range of applications in human-phone interaction, gaming, and many others. However, built-in sensors that detect subtle motion changes (e.g. accelerometers), might also reveal information about taps on touch screens: the main user input mode. Few researchers have already demonstrated the idea of exploiting motion sensors as side-channels into inferring keystrokes. Taken at most as initial explorations, much research is still needed to analyze the practicality of the new threat and examine various aspects of its implementation. One important aspect affecting directly the attack effectiveness is the selection of the right combination of sensors, to supply inference data. Although other aspects also play crucial role (e.g. the features set), we start in this paper by focusing on the comparison of different available sensors, in terms of the inference accuracy. We consider individual sensors shipped on Android phones, and study few options of preprocessing their raw datasets as well as fusing several sensors' readings. Our results indicate an outstanding performance of the gyroscope, and the potential of sensors data fusion. However, it seems that sensors with magnetometer component or the accelerometer alone have less benefit in the context of the adverted attack.

KW - Android

KW - Motion sensors

KW - Sensor-based attack

KW - Side-channel attack

KW - Smartphone security

KW - Touchscreen taps inference

UR - http://www.scopus.com/inward/record.url?scp=84901808968&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84901808968&partnerID=8YFLogxK

U2 - 10.5614/itbj.ict.res.appl.2013.7.2.2

DO - 10.5614/itbj.ict.res.appl.2013.7.2.2

M3 - Article

VL - 7

SP - 117

EP - 136

JO - Journal of ICT Research and Applications

JF - Journal of ICT Research and Applications

SN - 2337-5787

IS - 2

ER -