Towards detection of juice filming charging attacks via supervised CPU usage analysis on smartphones

Weizhi Meng, Lijun Jiang, Kim Kwang Raymond Choo, Yu Wang*, Chong Jiang

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

Abstract

Mobile devices, such as Android and iOS devices, are an attractive target for cyber-criminals, due to the amount of private data that can be accessed or stored on such devices. As public charging facilities become more commonplace, phone charging attacks are no longer fiction. Juice filming charging (JFC) attack is a particular phone charging threat, which can capture or infer users’ private information by automatically recording screen information from mobile devices during the entire charging process. In this work, we first investigate the types of phone applications users would interact with the most when charging their devices. Then, we propose a detection approach for JFC attacks solely by analyzing CPU usage. In the evaluation, we collect data from a total of 187 participants, and the findings show that our approach using the SVM classifier can achieve better performance than other approaches. Our work complements existing security mechanisms against charging threats.

Original languageEnglish
JournalComputers and Electrical Engineering
Volume78
Pages (from-to)230-241
ISSN0045-7906
DOIs
Publication statusPublished - 1 Sep 2019

Keywords

  • Android and iOS security
  • Charging threat
  • CPU usage analysis
  • JFC attack
  • Supervised machine learning

Cite this

Meng, Weizhi ; Jiang, Lijun ; Choo, Kim Kwang Raymond ; Wang, Yu ; Jiang, Chong. / Towards detection of juice filming charging attacks via supervised CPU usage analysis on smartphones. In: Computers and Electrical Engineering. 2019 ; Vol. 78. pp. 230-241.
@article{39a7436cd8f7470582b6eef21bba79cd,
title = "Towards detection of juice filming charging attacks via supervised CPU usage analysis on smartphones",
abstract = "Mobile devices, such as Android and iOS devices, are an attractive target for cyber-criminals, due to the amount of private data that can be accessed or stored on such devices. As public charging facilities become more commonplace, phone charging attacks are no longer fiction. Juice filming charging (JFC) attack is a particular phone charging threat, which can capture or infer users’ private information by automatically recording screen information from mobile devices during the entire charging process. In this work, we first investigate the types of phone applications users would interact with the most when charging their devices. Then, we propose a detection approach for JFC attacks solely by analyzing CPU usage. In the evaluation, we collect data from a total of 187 participants, and the findings show that our approach using the SVM classifier can achieve better performance than other approaches. Our work complements existing security mechanisms against charging threats.",
keywords = "Android and iOS security, Charging threat, CPU usage analysis, JFC attack, Supervised machine learning",
author = "Weizhi Meng and Lijun Jiang and Choo, {Kim Kwang Raymond} and Yu Wang and Chong Jiang",
year = "2019",
month = "9",
day = "1",
doi = "10.1016/j.compeleceng.2019.07.008",
language = "English",
volume = "78",
pages = "230--241",
journal = "Computers and Electrical Engineering",
issn = "0045-7906",
publisher = "Elsevier",

}

Towards detection of juice filming charging attacks via supervised CPU usage analysis on smartphones. / Meng, Weizhi; Jiang, Lijun; Choo, Kim Kwang Raymond; Wang, Yu; Jiang, Chong.

In: Computers and Electrical Engineering, Vol. 78, 01.09.2019, p. 230-241.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Towards detection of juice filming charging attacks via supervised CPU usage analysis on smartphones

AU - Meng, Weizhi

AU - Jiang, Lijun

AU - Choo, Kim Kwang Raymond

AU - Wang, Yu

AU - Jiang, Chong

PY - 2019/9/1

Y1 - 2019/9/1

N2 - Mobile devices, such as Android and iOS devices, are an attractive target for cyber-criminals, due to the amount of private data that can be accessed or stored on such devices. As public charging facilities become more commonplace, phone charging attacks are no longer fiction. Juice filming charging (JFC) attack is a particular phone charging threat, which can capture or infer users’ private information by automatically recording screen information from mobile devices during the entire charging process. In this work, we first investigate the types of phone applications users would interact with the most when charging their devices. Then, we propose a detection approach for JFC attacks solely by analyzing CPU usage. In the evaluation, we collect data from a total of 187 participants, and the findings show that our approach using the SVM classifier can achieve better performance than other approaches. Our work complements existing security mechanisms against charging threats.

AB - Mobile devices, such as Android and iOS devices, are an attractive target for cyber-criminals, due to the amount of private data that can be accessed or stored on such devices. As public charging facilities become more commonplace, phone charging attacks are no longer fiction. Juice filming charging (JFC) attack is a particular phone charging threat, which can capture or infer users’ private information by automatically recording screen information from mobile devices during the entire charging process. In this work, we first investigate the types of phone applications users would interact with the most when charging their devices. Then, we propose a detection approach for JFC attacks solely by analyzing CPU usage. In the evaluation, we collect data from a total of 187 participants, and the findings show that our approach using the SVM classifier can achieve better performance than other approaches. Our work complements existing security mechanisms against charging threats.

KW - Android and iOS security

KW - Charging threat

KW - CPU usage analysis

KW - JFC attack

KW - Supervised machine learning

U2 - 10.1016/j.compeleceng.2019.07.008

DO - 10.1016/j.compeleceng.2019.07.008

M3 - Journal article

VL - 78

SP - 230

EP - 241

JO - Computers and Electrical Engineering

JF - Computers and Electrical Engineering

SN - 0045-7906

ER -