A Comparison of Features for Android Malware Detection

@article{Leeds2017ACO,
  title={A Comparison of Features for Android Malware Detection},
  author={Matthew Leeds and Miclain Keffeler and Travis Atkison},
  journal={Proceedings of the SouthEast Conference},
  year={2017}
}
With the increase in mobile device use, there is a greater need for increasingly sophisticated malware detection algorithms. The research presented in this paper examines two types of features of Android applications, permission requests and system calls, as a way to detect malware. We are able to differentiate between benign and malicious apps by applying a machine learning algorithm. The model that is presented here achieved a classification accuracy of around 80% using permissions and 60… 

Figures from this paper

Examining Features for Android Malware Detection

TLDR
The research presented in this paper expands upon previous work that applied machine learning techniques to the area of Android malware detection by examining Java API call data as a method for malware detection using the JAVA API call feature.

Large-scale Malware Automatic Detection Based On Multiclass Features and Machine Learning

TLDR
A large-scale malware detection system based on multiclass features and machine learning, and selects the most suitable algorithm "ensemble learning" by comparing the detection accuracies of 7 algorithms, then adjusting and optimizing the related parameter to achieve the highest accuracy.

Android Mobile Malware Detection Using Machine Learning: A Systematic Review

TLDR
This paper provides a systematic review of ML-based Android malware detection techniques and critically evaluates 106 carefully selected articles and highlights their strengths and weaknesses as well as potential improvements.

A State of Art Survey for Understanding Malware Detection Approaches in Android Operating System

TLDR
A thorough comparison that summarizes and analyses the various detection techniques of Android malware detection is included, which suggests that machine learning is an effective and promising way to detect Android malware.

Android Malware Detection by Machine Learning Apprehension and Static Feature Characterization

TLDR
This paper represents a model, which will help the developers or antivirus launcher to detect malware if it is repackaged, and a vocabulary was also created to identify the malicious code.

Analysis of Android Malware Detection Techniques: A Systematic Review

TLDR
The results show that most detection techniques are not very effective to detect zero-day malware and other variants that deploy obfuscation to evade detection.

Android Malware Detection Using Complex-Flows

TLDR
A new technique to detect mobile malware based on information flow analysis that accurately captures the complex behavior exhibited by both recent malware and benign applications is proposed.

Constructing Features for Detecting Android Malicious Applications: Issues, Taxonomy and Directions

TLDR
This paper provides a clear and comprehensive survey of the state-of-the-art work that detects malapps by characterizing behaviors of apps with various types of features, and highlights the issues of exploring effective features from apps, provide the taxonomy of these features and indicate the future directions.

NADM: Neural Network for Android Detection Malware

TLDR
A Neural Network for Android Detection of Malware (NADM) performs an analysis process to gather features of Android applications and can achieve a high accuracy system and has been applied in sProtect on Google Play.

One-dimensional convolutional neural networks for Android malware detection

  • Chihiro HasegawaH. Iyatomi
  • Computer Science
    2018 IEEE 14th International Colloquium on Signal Processing & Its Applications (CSPA)
  • 2018
TLDR
This paper proposes an accurate and light-weight Android malware detection method that treats very limited part of raw APK (Android application package) file of the target as a short string and analyzes it with one-dimensional convolutional neural network (1-D CNN).

References

SHOWING 1-10 OF 31 REFERENCES

Preliminary Results of Applying Machine Learning Algorithms to Android Malware Detection

  • M. LeedsT. Atkison
  • Computer Science
    2016 International Conference on Computational Science and Computational Intelligence (CSCI)
  • 2016
TLDR
The preliminary research presented in this paper focuses on examining permission requests made by Android apps as a means for detecting malware by using a machine learning algorithm, and is able to differentiate between benign and malicious apps.

Classification of Android Malware Applications using Feature Selection and Classification Algorithms

TLDR
This paper proposes an approach for Android malware classification based on features selection and classification algorithms, which uses the permissions used in the Android app as features, to differentiate between the malware apps and goodware apps.

A Machine Learning Approach to Android Malware Detection

  • Justin SahsL. Khan
  • Computer Science
    2012 European Intelligence and Security Informatics Conference
  • 2012
TLDR
A machine learning-based system for the detection of malware on Android devices that extracts a number of features and trains a One-Class Support Vector Machine in an offline (off-device) manner, in order to leverage the higher computing power of a server or cluster of servers.

Detecting Malware for Android Platform: An SVM-Based Approach

TLDR
A malware detection scheme for Android platform using an SVM-based approach, which integrates both risky permission combinations and vulnerable API calls and use them as features in the SVM algorithm is studied.

Evaluation of Android Malware Detection Based on System Calls

TLDR
This paper evaluates a few techniques for detecting malicious Android applications on a repository level and shows that system-call based techniques are viable to be used in practice, suggesting that more heavyweight approaches should be thoroughly (re)evaluated.

Permission-Based Android Malware Detection

TLDR
The proposed framework intends to develop a machine learning-based malware detection system on Android to detect malware applications and to enhance security and privacy of smartphone users.

Android Malware Detection Based on System Calls

TLDR
The technique performs automatic classification based on tracking system calls while applications are executed in a sandbox environment and shows that even simplistic feature choices are highly effective, suggesting that more heavyweight approaches should be thoroughly (re)evaluated.

Intelligent Approach for Android Malware Detection

TLDR
A self-adaptive neuro-fuzzy inference system to classify the Android apps into malware and goodware based on system permissions is introduced and it is concluded that the proposed classifier can be effective in Android protection.

A Probabilistic Discriminative Model for Android Malware Detection with Decompiled Source Code

TLDR
This paper proposes a probabilistic discriminative model based on regularized logistic regression that substantially outperforms the state-of-the-art methods for Android malware detection with application permissions and achieves the best detection results by combining both decompiled source code and application permissions.

ANASTASIA: ANdroid mAlware detection using STatic analySIs of Applications

TLDR
This work proposes ANASTASIA, a system to detect malicious Android applications through statically analyzing applications' behaviors that provides a more complete coverage of security behaviors when compared to state-of-the-art solutions.