A Probabilistic Diffusion Scheme for Anomaly Detection on Smartphones

Alpcan, Tansu; Bauckhage, Christian; Schmidt, Aubrey-Derrick

doi:10.1007/978-3-642-12368-9_3

Cited by 13 publications

(7 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The approach in [2] includes a static analysis system for analysing Android market applications and uses automated reverse engineering and refactoring of binary application packages to mitigate security and privacy threats driven by security preferences of the user. The approach is based on a probabilistic diffusion scheme using device usage patterns [1]. The Android Application Sandbox [4] has also been used for both static and dynamic analysis on Android programs and for detecting suspicious applications automatically based on the collaborative detection [20].…”

Section: General Mobile Malware Detection Techniquesmentioning

confidence: 99%

MBotCS: A Mobile Botnet Detection System Based on Machine Learning

Meng

Spanoudakis

2016

Lecture Notes in Computer Science

View full text Add to dashboard Cite

This is the accepted version of the paper.This version of the publication may differ from the final published version. Abstract. As the use of mobile devices spreads dramatically, hackers have started making use of mobile botnets to steal user information or perform other malicious attacks. To address this problem, in this paper we propose a mobile botnet detection system, called MBotCS. MBotCS can detect mobile device traffic indicative of the presence of a mobile botnet based on prior training using machine learning techniques. Our approach has been evaluated using real mobile device traffic captured from Android mobile devices, running normal apps and mobile botnets. In the evaluation, we investigated the use of 5 machine learning classifier algorithms and a group of machine learning box algorithms with different validation schemes. We have also evaluated the effect of our approach with respect to its effect on the overall performance and battery consumption of mobile devices. Permanent repository link

show abstract

Section: General Mobile Malware Detection Techniquesmentioning

confidence: 99%

MBotCS: A Mobile Botnet Detection System Based on Machine Learning

Meng

Spanoudakis

2016

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Alpcan et al proposed the use of a "novel probabilistic diffusion scheme for detecting anomalies possibly indicating malware which is based on device usage patterns" [27]. Behl and Behl [26] recommend solutions to protect end-users from the potential privacy and security vulnerabilities of cloud systems.…”

Section: Other Privacy Frameworkmentioning

confidence: 99%

Reference Architectures for Privacy Preservation in Cloud-based IoT Applications

Addo¹,

Ahamed²,

Yau³

et al. 2014

STSC

View full text Add to dashboard Cite

As the promise of the Internet of Things (IoT) materializes in our everyday lives, we are often challenged with a number of concerns regarding the efficacy of the current data privacy solutions that support the pervasive components at play in IoT. The privacy and security concerns surrounding IoT applications often manifests themselves as a threat to end-user adoption and negatively impacts trust among end-users. In this paper, we present a reference software architectures for building cloud-enabled IoT applications in support of collaborative pervasive systems aimed at achieving trustworthiness among end-users in IoT scenarios. We describe a case study that leverages this reference architecture to protect sensitive user data in IoT application implementation. We then evaluate the response data from our end-user survey. In addition we present a Secure, Private and Trustworthy protocol (named SPTP) that was prototyped for addressing critical security, privacy and trust concerns surrounding mobile, pervasive and cloud services in Collective Intelligence (CI) scenarios. We present our evaluation criteria for the proposed protocol, our results and future work.

show abstract

“…Despite the fact that all the aforementioned researches have significantly contributed to the anomaly‐based IDS for mobile devices issued, several important problems remain unsolved. Currently, the main disadvantage of most IDS for mobile devices that use anomaly detection techniques is the high false alarm rate (FPR) . Hence, there is an urgent need for methods that substantially improve the detection rate while minimising false alarms.…”

Section: Related Workmentioning

confidence: 99%

Evaluation of anomaly‐based IDS for mobile devices using machine learning classifiers

Damopoulos

Menesidou

Kambourakis

et al. 2011

Security Comm Networks

View full text Add to dashboard Cite

Mobile devices have evolved and experienced an immense popularity over the last few years. This growth however has exposed mobile devices to an increasing number of security threats. Despite the variety of peripheral protection mechanisms described in the literature, authentication and access control cannot provide integral protection against intrusions. Thus, a need for more intelligent and sophisticated security controls such as intrusion detection systems (IDSs) is necessary. Whilst much work has been devoted to mobile device IDSs, research on anomaly-based or behaviour-based IDS for such devices has been limited leaving several problems unsolved. Motivated by this fact, in this paper, we focus on anomaly-based IDS for modern mobile devices. A dataset consisting of iPhone users data logs has been created, and various classification and validation methods have been evaluated to assess their effectiveness in detecting misuses. Specifically, the experimental procedure includes and cross-evaluates four machine learning algorithms (i.e. Bayesian networks, radial basis function, K-nearest neighbours and random Forest), which classify the behaviour of the end-user in terms of telephone calls, SMS and Web browsing history. In order to detect illegitimate use of service by a potential malware or a thief, the experimental procedure examines the aforementioned services independently as well as in combination in a multimodal fashion. The results are very promising showing the ability of at least one classifier to detect intrusions with a high true positive rate of 99.8%.

show abstract

A Probabilistic Diffusion Scheme for Anomaly Detection on Smartphones

Cited by 13 publications

References 25 publications

MBotCS: A Mobile Botnet Detection System Based on Machine Learning

MBotCS: A Mobile Botnet Detection System Based on Machine Learning

Reference Architectures for Privacy Preservation in Cloud-based IoT Applications

Evaluation of anomaly‐based IDS for mobile devices using machine learning classifiers

Contact Info

Product

Resources

About