2018 1st International Conference on Data Intelligence and Security (ICDIS) 2018
DOI: 10.1109/icdis.2018.00044
|View full text |Cite
|
Sign up to set email alerts
|

A Network-Based Framework for Mobile Threat Detection

Abstract: Mobile malware attacks increased three folds in the past few years and continued to expand with the growing number of mobile users. Adversary uses a variety of evasion techniques to avoid detection by traditional systems, which increase the diversity of malicious applications. Thus, there is a need for an intelligent system that copes with this issue. This paper proposes a machine learning (ML) based framework to counter rapid evolution of mobile threats. This model is based on flow-based features, that will w… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
8
0

Year Published

2018
2018
2023
2023

Publication Types

Select...
4
1
1
1

Relationship

1
6

Authors

Journals

citations
Cited by 7 publications
(8 citation statements)
references
References 18 publications
0
8
0
Order By: Relevance
“…In [9], the researchers proposed a ML classification model in creating the network-based IDS and is mainly for the threats induced in mobile devices network. As we know the threats in the mobile world increase rapidly, and the attackers steal sensitive information, exploiting the users by sending unwanted SMS.…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation
“…In [9], the researchers proposed a ML classification model in creating the network-based IDS and is mainly for the threats induced in mobile devices network. As we know the threats in the mobile world increase rapidly, and the attackers steal sensitive information, exploiting the users by sending unwanted SMS.…”
Section: Related Workmentioning
confidence: 99%
“…KL divergence changes close to similar data points focuses on joint probabilities. The expansion of this term to loss function and it benefits dimensionality decreases as shown in equation (9).…”
Section: Parameterized Rectified Linear Activation Functionmentioning
confidence: 99%
“…Either signature (misuse detection) of well-known assaults or Behaviour-based techniques are utilized to detect these behaviours (anomaly detection). Behaviourbased systems identify deviations from the typical behaviour profile and can detect unknown attacks, whereas signature-based systems can only detect attacks for which they are trained to notify [26,27].…”
Section: Intrusion Detection System (Ids) and Machine Learningmentioning
confidence: 99%
“…Each application assigns a unique User ID and a set of permissions at the app installation time. Android developers must request permission to use these special features in a standard format that is parsed at installation time [2]. The permission model used in Android has many advantages and can be effective in preventing malware while also informing users what applications are capable of doing once installed [3].…”
Section: Introductionmentioning
confidence: 99%