Towards a fair comparison and realistic evaluation framework of android malware detectors based on static analysis and machine learning

Published in

Computers & security(2022)

External Links:

Generate Graph DownloadPDF

TL;DR

An analysis of 10 influential research works on Android malware detection using a common evaluation framework concludes that the studied ML-based detectors have been evaluated optimistically, which justifies the good published results.

Authors

Borja Molina-Coronado

1 papers

U. Mori

1 papers

A. Mendiburu

1 papers

J. Miguel-Alonso

1 papers

References78 items

A two-steps approach to improve the performance of Android malware detectors

On Impact of Semantically Similar Apps in Android Malware Datasets

SemiDroid: a behavioral malware detector based on unsupervised machine learning techniques using feature selection approaches

Enhancing State-of-the-art Classifiers with API Semantics to Detect Evolved Android Malware

Maat

Towards a fair comparison and realistic evaluation framework of android malware detectors based on static analysis and machine learning

Published in

Computers & security(2022)

External Links:

Generate Graph DownloadPDF

TL;DR

Authors

Borja Molina-Coronado

1 papers

U. Mori

1 papers

A. Mendiburu

1 papers

J. Miguel-Alonso

1 papers

References78 items

A two-steps approach to improve the performance of Android malware detectors

On Impact of Semantically Similar Apps in Android Malware Datasets

SemiDroid: a behavioral malware detector based on unsupervised machine learning techniques using feature selection approaches

Enhancing State-of-the-art Classifiers with API Semantics to Detect Evolved Android Malware

Maat

AVclass2: Massive Malware Tag Extraction from AV Labels

Array programming with NumPy

Survey of Network Intrusion Detection Methods From the Perspective of the Knowledge Discovery in Databases Process

Obfuscapk: An open-source black-box obfuscation tool for Android apps

Learning under Concept Drift: A Review

A survey on semi-supervised learning

Don't Pick the Cherry: An Evaluation Methodology for Android Malware Detection Methods

A Multimodal Deep Learning Method for Android Malware Detection Using Various Features

A state-of-the-art survey of malware detection approaches using data mining techniques

Malware Dynamic Analysis Evasion Techniques

Learning from Imbalanced Data Sets

Toward Developing a Systematic Approach to Generate Benchmark Android Malware Datasets and Classification

Adversarial Examples: Opportunities and Challenges

TESSERACT: Eliminating Experimental Bias in Malware Classification across Space and Time

A Large-Scale Empirical Study on the Effects of Code Obfuscations on Android Apps and Anti-Malware Products

Eight Years of Rider Measurement in the Android Malware Ecosystem

[Journal First] Lightweight, Obfuscation-Resilient Detection and Family Identification of Android Malware

SAMADroid: A Novel 3-Level Hybrid Malware Detection Model for Android Operating System

DroidDet: Effective and robust detection of android malware using static analysis along with rotation forest model

A review of smart home applications based on Internet of Things

Static analysis of android apps: A systematic literature review

Android Malware Clustering through Malicious Payload Mining

Deep Ground Truth Analysis of Current Android Malware

Context-Aware, Adaptive, and Scalable Android Malware Detection Through Online Learning

Yes, Machine Learning Can Be More Secure! A Case Study on Android Malware Detection

AndroDialysis: Analysis of Android Intent Effectiveness in Malware Detection

Is the data on your wearable device secure? An Android Wear smartwatch case study

The Evolution of Android Malware and Android Analysis Techniques

MaMaDroid: Detecting Android Malware by Building Markov Chains of Behavioral Models

SandPrint: Fingerprinting Malware Sandboxes to Provide Intelligence for Sandbox Evasion

Testing android malware detectors against code obfuscation: a systematization of knowledge and unified methodology

Toward Engineering a Secure Android Ecosystem

An HMM and structural entropy based detector for Android malware: An empirical study

AndroZoo: Collecting Millions of Android Apps for the Research Community

Practical Black-Box Attacks against Machine Learning

DroidDetector: Android Malware Characterization and Detection Using Deep Learning

ICCDetector: ICC-Based Malware Detection on Android

Experimental Study with Real-world Data for Android App Security Analysis using Machine Learning

Reviewer Integration and Performance Measurement for Malware Detection

Stealth attacks: An extended insight into the obfuscation effects on Android malware

Are Your Training Datasets Yet Relevant? - An Investigation into the Importance of Timeline in Machine Learning-Based Malware Detection

Android Security: A Survey of Issues, Malware Penetration, and Defenses

Empirical assessment of machine learning-based malware detectors for Android

Mobile-Sandbox: combining static and dynamic analysis with machine-learning techniques

AndRadar: Fast Discovery of Android Applications in Alternative Markets

Evading android runtime analysis via sandbox detection

Dissecting Android Malware: Characterization and Evolution

Scikit-learn: Machine Learning in Python

Active Learning by Querying Informative and Representative Examples

Whose Vote Should Count More: Optimal Integration of Labels from Labelers of Unknown Expertise

Learning from Imbalanced Data

A survey of cross-validation procedures for model selection

An in-vehicle infotainment software architecture based on google android

Limits of Static Analysis for Malware Detection

The Elements of Statistical Learning: Data Mining, Inference, and Prediction

Small Sample Size Effects in Statistical Pattern Recognition: Recommendations for Practitioners

This paper is included in the Proceedings of the 31st USENIX Security Symposium.

Measuring and Modeling the Label Dynamics of Online Anti-Malware Engines

PermPair: Android Malware Detection Using Permission Pairs

When Malware is Packin' Heat; Limits of Machine Learning Classifiers Based on Static Analysis Features

Androguard, 2018. [Online] Available: https: //androguard.readthedocs.io/en/latest

DREBIN: Effective and Explainable Detection of Android Malware in Your Pocket

Federico Maggi, Christian Platzer, Stefano Zanero, and Sotiris Ioannidis

Ieee Transactions on Information Forensics and Security 1 Catch Me If You Can: Evaluating Android Anti-malware against Transformation Attacks

Techniques: A Large-Scale Investigation in the Wild

We highlight the lack of reproducibility of published work in this area

analyze the performance of state-of-the-art ML-based Android malware detection approaches when the above factors are taken into account

Mobile operating systems' market share worldwide from

Android security & privacy

Mobile malware evolution 2020

What is a pua ( potentially unwanted application ) or pup ( potentially unwanted program ) ? , 2022

Field of Study

Computer Science

Journal Information

Name

Comput. Secur.

Page

102996

Volume

124

Venue Information

Name

Computers & security

Type

journal

URL

http://www.sciencedirect.com/science/journal/01674048

Alternate Names

Comput Secur
Computers & Security
Comput secur

TL;DR

Authors

References78 items

A two-steps approach to improve the performance of Android malware detectors

On Impact of Semantically Similar Apps in Android Malware Datasets

SemiDroid: a behavioral malware detector based on unsupervised machine learning techniques using feature selection approaches

Enhancing State-of-the-art Classifiers with API Semantics to Detect Evolved Android Malware

Maat

TL;DR

Authors

References78 items

A two-steps approach to improve the performance of Android malware detectors

On Impact of Semantically Similar Apps in Android Malware Datasets

SemiDroid: a behavioral malware detector based on unsupervised machine learning techniques using feature selection approaches

Enhancing State-of-the-art Classifiers with API Semantics to Detect Evolved Android Malware

Maat

AVclass2: Massive Malware Tag Extraction from AV Labels

Array programming with NumPy

Survey of Network Intrusion Detection Methods From the Perspective of the Knowledge Discovery in Databases Process

Obfuscapk: An open-source black-box obfuscation tool for Android apps

Learning under Concept Drift: A Review

A survey on semi-supervised learning

Don't Pick the Cherry: An Evaluation Methodology for Android Malware Detection Methods

A Multimodal Deep Learning Method for Android Malware Detection Using Various Features

A state-of-the-art survey of malware detection approaches using data mining techniques

Malware Dynamic Analysis Evasion Techniques

Learning from Imbalanced Data Sets

Toward Developing a Systematic Approach to Generate Benchmark Android Malware Datasets and Classification

Adversarial Examples: Opportunities and Challenges

TESSERACT: Eliminating Experimental Bias in Malware Classification across Space and Time

A Large-Scale Empirical Study on the Effects of Code Obfuscations on Android Apps and Anti-Malware Products

Eight Years of Rider Measurement in the Android Malware Ecosystem

[Journal First] Lightweight, Obfuscation-Resilient Detection and Family Identification of Android Malware

SAMADroid: A Novel 3-Level Hybrid Malware Detection Model for Android Operating System

DroidDet: Effective and robust detection of android malware using static analysis along with rotation forest model

A review of smart home applications based on Internet of Things

Static analysis of android apps: A systematic literature review

Android Malware Clustering through Malicious Payload Mining

Deep Ground Truth Analysis of Current Android Malware

Context-Aware, Adaptive, and Scalable Android Malware Detection Through Online Learning

Yes, Machine Learning Can Be More Secure! A Case Study on Android Malware Detection

AndroDialysis: Analysis of Android Intent Effectiveness in Malware Detection

Is the data on your wearable device secure? An Android Wear smartwatch case study

The Evolution of Android Malware and Android Analysis Techniques

MaMaDroid: Detecting Android Malware by Building Markov Chains of Behavioral Models

SandPrint: Fingerprinting Malware Sandboxes to Provide Intelligence for Sandbox Evasion

Testing android malware detectors against code obfuscation: a systematization of knowledge and unified methodology

Toward Engineering a Secure Android Ecosystem

An HMM and structural entropy based detector for Android malware: An empirical study

AndroZoo: Collecting Millions of Android Apps for the Research Community

Practical Black-Box Attacks against Machine Learning

DroidDetector: Android Malware Characterization and Detection Using Deep Learning

ICCDetector: ICC-Based Malware Detection on Android

Experimental Study with Real-world Data for Android App Security Analysis using Machine Learning

Reviewer Integration and Performance Measurement for Malware Detection

Stealth attacks: An extended insight into the obfuscation effects on Android malware

Securing Android

Are Your Training Datasets Yet Relevant? - An Investigation into the Importance of Timeline in Machine Learning-Based Malware Detection

Android Security: A Survey of Issues, Malware Penetration, and Defenses

Empirical assessment of machine learning-based malware detectors for Android

Mobile-Sandbox: combining static and dynamic analysis with machine-learning techniques

AndRadar: Fast Discovery of Android Applications in Alternative Markets

Evading android runtime analysis via sandbox detection

Dissecting Android Malware: Characterization and Evolution

Scikit-learn: Machine Learning in Python

Active Learning by Querying Informative and Representative Examples

Whose Vote Should Count More: Optimal Integration of Labels from Labelers of Unknown Expertise

Learning from Imbalanced Data

A survey of cross-validation procedures for model selection

An in-vehicle infotainment software architecture based on google android

Limits of Static Analysis for Malware Detection

The Elements of Statistical Learning: Data Mining, Inference, and Prediction

Small Sample Size Effects in Statistical Pattern Recognition: Recommendations for Practitioners

This paper is included in the Proceedings of the 31st USENIX Security Symposium.

Kaspersky Labs

Measuring and Modeling the Label Dynamics of Online Anti-Malware Engines

PermPair: Android Malware Detection Using Permission Pairs

When Malware is Packin' Heat; Limits of Machine Learning Classifiers Based on Static Analysis Features

Androguard, 2018. [Online] Available: https: //androguard.readthedocs.io/en/latest

DREBIN: Effective and Explainable Detection of Android Malware in Your Pocket