POSTER: Breaking the Android Pattern Lock Screen with Neural Networks and Smudge Attacks

Panagiotis Andriotis; Theo Tryfonas; Zhaoqian Yu

POSTER: Breaking the Android Pattern Lock Screen with Neural Networks and Smudge Attacks

Panagiotis Andriotis, Theo Tryfonas, Zhaoqian Yu

Research output: Contribution to conference › Conference Poster › peer-review

345 Downloads (Pure)

Abstract

The Android pattern lock screen is a popular mechanism offered for user authentication on smartphones and tablets. It is a graphical password scheme that provides usability and memorability. Despite the wide password space of the mechanism, there exist well-known techniques (such as smudge attacks) questioning its security strengths. With this study we aim to demonstrate that if we use previous knowledge, which describes the results of biased password input, in addition to a method that extracts traces of residues from a mobile device screen, we will be able to develop a lightweight automated tool capable to predict the user’s chosen password.

Original language	English
Pages	1-2
Number of pages	2
Publication status	Published - Jul 2014
Event	7th ACM Conference on Security and Privacy in Wireless and Mobile Networks - Oxford, United Kingdom Duration: 23 Jul 2014 → 25 Jul 2014

Conference

Conference	7th ACM Conference on Security and Privacy in Wireless and Mobile Networks
Country/Territory	United Kingdom
City	Oxford
Period	23/07/14 → 25/07/14

Keywords

Graphical
password
heuristics
forensics
tool
smartphone
prediction

Access to Document

Full-text PDF (accepted author manuscript)
This is the author accepted manuscript (AAM). The final published version (version of record) is available online via ACM. Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 133 KBLicence: CC BY-NC

Handle.net

Persistent link

Forensic Tools Against Illegal Use of Internet (ForToo)
Andriotis, P. (Researcher), Haghighi, M. (Researcher), Li, S. (Researcher), Oikonomou, G. (Researcher), Wojcik, M. (Researcher) & Tryfonas, T. (Principal Investigator)
17/06/11 → 16/10/14
Project: Research

Cite this

@conference{21c5d517380340f4ba748e7585dcd8cd,

title = "POSTER: Breaking the Android Pattern Lock Screen with Neural Networks and Smudge Attacks",

abstract = "The Android pattern lock screen is a popular mechanism offered for user authentication on smartphones and tablets. It is a graphical password scheme that provides usability and memorability. Despite the wide password space of the mechanism, there exist well-known techniques (such as smudge attacks) questioning its security strengths. With this study we aim to demonstrate that if we use previous knowledge, which describes the results of biased password input, in addition to a method that extracts traces of residues from a mobile device screen, we will be able to develop a lightweight automated tool capable to predict the user{\textquoteright}s chosen password.",

keywords = "Graphical, password, heuristics, forensics, tool, smartphone, prediction",

author = "Panagiotis Andriotis and Theo Tryfonas and Zhaoqian Yu",

year = "2014",

month = jul,

language = "English",

pages = "1--2",

note = "7th ACM Conference on Security and Privacy in Wireless and Mobile Networks ; Conference date: 23-07-2014 Through 25-07-2014",

}

TY - CONF

T1 - POSTER: Breaking the Android Pattern Lock Screen with Neural Networks and Smudge Attacks

AU - Andriotis, Panagiotis

AU - Tryfonas, Theo

AU - Yu, Zhaoqian

PY - 2014/7

Y1 - 2014/7

N2 - The Android pattern lock screen is a popular mechanism offered for user authentication on smartphones and tablets. It is a graphical password scheme that provides usability and memorability. Despite the wide password space of the mechanism, there exist well-known techniques (such as smudge attacks) questioning its security strengths. With this study we aim to demonstrate that if we use previous knowledge, which describes the results of biased password input, in addition to a method that extracts traces of residues from a mobile device screen, we will be able to develop a lightweight automated tool capable to predict the user’s chosen password.

AB - The Android pattern lock screen is a popular mechanism offered for user authentication on smartphones and tablets. It is a graphical password scheme that provides usability and memorability. Despite the wide password space of the mechanism, there exist well-known techniques (such as smudge attacks) questioning its security strengths. With this study we aim to demonstrate that if we use previous knowledge, which describes the results of biased password input, in addition to a method that extracts traces of residues from a mobile device screen, we will be able to develop a lightweight automated tool capable to predict the user’s chosen password.

KW - Graphical

KW - password

KW - heuristics

KW - forensics

KW - tool

KW - smartphone

KW - prediction

M3 - Conference Poster

SP - 1

EP - 2

T2 - 7th ACM Conference on Security and Privacy in Wireless and Mobile Networks

Y2 - 23 July 2014 through 25 July 2014

ER -

POSTER: Breaking the Android Pattern Lock Screen with Neural Networks and Smudge Attacks

Abstract

Conference

Keywords

Access to Document

Handle.net

Fingerprint

Projects

Forensic Tools Against Illegal Use of Internet (ForToo)

Cite this