Modeling and Analysis of Intentional And Unintentional Security Vulnerabilities in a Mobile Platform Page: 8
xi, 149 pages : illustrations (chiefly color)View a full description of this dissertation.
Extracted Text
The following text was automatically extracted from the image on this page using optical character recognition software:
mistakenly being pronounced.
To profile user behavior in regard phone authentication: I used EEG (brainwave activity patterns)
to identify repeated activities a user performs when using a phone, such as swiping, pinch-
ing, tapping. I extracted these features from the EEG experiment and used a machine
learning model to distinguish between these activities, with 85% accuracy. This way user
intention can be revealed and can be used in mobile phone security such as authentication.
One advantage of using EEG in authentication is that it can provide a biometric using EEG
for authentication [20]. However, in this work I took the first step towards solving the
authentication problem and I present this as future work.
1.7. Dissertation Outline
Chapter 1: This chapter provide an introduction to the concept of this dissertation. Further, it
summarizes the problem definition and the rest of the document.
Chapter 2: Intention is a key term in this dissertation. In this chapter, different types of intentions
are identified and its importance are discussed.
Chapter 3: This chapter briefly describes the usage of intention identification. Four different prob-
lems are explained in this chapter related to two different types of intentions (user-intention
and app-intention). These four applications are 1. Malware identification, 2. User role iden-
tification, 3. Context-aware encryption, and 4. EEG based behavior identification. Each
of these problems are solved using different type of intention identification. The following
chapters describe how each problem is solved using the introduced intention identification
concepts.
Chapter 4: Task-intention is part of the app-intention. Identifying the task-intention is the first
step of malware identification in my approach. This chapter describes on how to deter-
mine the task-intention of an android app by using machine learning models. This task-
intention identification should not be confused with the malicious-intention identification.
Task-intention simply says the main functionality of the application. On the other hand,
malicious-intention identification reveals whether the app is malicious or not. However,
the task-intention is used to determine if an app is malicious or not.8
Upcoming Pages
Here’s what’s next.
Search Inside
This dissertation can be searched. Note: Results may vary based on the legibility of text within the document.
Tools / Downloads
Get a copy of this page or view the extracted text.
Citing and Sharing
Basic information for referencing this web page. We also provide extended guidance on usage rights, references, copying or embedding.
Reference the current page of this Dissertation.
Mohamed Issadeen, Mohamed Fazeen. Modeling and Analysis of Intentional And Unintentional Security Vulnerabilities in a Mobile Platform, dissertation, December 2014; Denton, Texas. (https://digital.library.unt.edu/ark:/67531/metadc700067/m1/22/: accessed July 18, 2024), University of North Texas Libraries, UNT Digital Library, https://digital.library.unt.edu; .