Malware Detection in Android Systems with Traditional Machine Learning Models: A Survey

Bayazit, Esra Calik; Şahingöz, Özgür Koray; Doğan, Buket

doi:10.1109/hora49412.2020.9152840

Cited by 24 publications

(11 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Decision trees are an easy to interpret machine learning approach commonly used for classification and problems. It is one of the most widely used classification techniques due to its low cost, ease of understanding, reliability, and high performance working with different data (Karatas et al, 2020;Bayazit et al, 2020). A decision tree is a method in which the learned function is represented as a decision tree.…”

Section: Decision Tree (Dt)mentioning

confidence: 99%

Detecting Internet of Things Attacks by Using Hybrid Learning and Feature Selection Method

BAYDOĞMUŞ¹

2021

European Journal of Science and Technology

View full text Add to dashboard Cite

Internet of Things (IoT) produces an enormous amount of data, which is used in all areas of our lives and increases the number of data on the Internet with each passing day. Smart watches, robot vacuum cleaners, refrigerators with cameras, and more can all be considered IoT devices. Ease of access to the Internet provides people with advantages as well as disadvantages. Malware and intruders have easier access to the devices we use and our information via the internet. At this point, data security gains great importance especially in IoT devices because accessing our personal data via smart watches or refrigerators we use can pose a great threat to individuals and their families. This study focus the importance of data preprocessing and developing a hybrid machine learning-based intrusion detection system (IDS) for IoT. Decision Tree, which is a popular machine learning algorithm, and n_Balot dataset were preferred for investigations. Accordingly, it is aimed to create a hybrid model by applying K-means and Decision Tree algorithms to the n_Balot dataset with under sampling and feature selection. In the data preprocessing, feature selection was performed with Chi-Square method and under sampling performed with RandomOverSampling method. Then, clustering was done by applying K-means to the processed dataset, and the results obtained with the clustering were classified with the Decision tree algorithm. As a result of the study, while the error rate was 0.39% in the predictions made only with the decision tree, the error rate was reduced to 0.01% with the developed hybrid model.

show abstract

Section: Decision Tree (Dt)mentioning

confidence: 99%

Detecting Internet of Things Attacks by Using Hybrid Learning and Feature Selection Method

BAYDOĞMUŞ¹

2021

European Journal of Science and Technology

View full text Add to dashboard Cite

show abstract

“…e study in [17] introduced the Android architecture, security mechanism, malware classification, and entire detection process, including sample collection, data preprocessing, feature selection, machine learning model construction, and experimental evaluation. e study in [18][19][20] comprehensively discussed static, dynamic, and hybrid detection techniques. e study in [21] mainly focused on mobile malware detection techniques, analysed signature-based detection, anomaly-based detection, and other traditional detection methods.…”

Section: Introductionmentioning

confidence: 99%

A Survey of Android Malware Static Detection Technology Based on Machine Learning

Zhu

Liu

2021

Mobile Information Systems

View full text Add to dashboard Cite

With the rapid growth of Android devices and applications, the Android environment faces more security threats. Malicious applications stealing usersʼ privacy information, sending text messages to trigger deductions, exploiting privilege escalation to control the system, etc., cause significant harm to end users. To detect Android malware, researchers have proposed various techniques, among which the machine learning-based methods with static features of apps as input vectors have apparent advantages in code coverage, operational efficiency, and massive sample detection. In this paper, we investigated Android applicationsʼ structure, analysed various sources of static features, reviewed the machine learning methods for detecting Android malware, studied the advantages and limitations of these methods, and discussed the future directions in this field. Our work will help researchers better understand the current research state, the benefits and weaknesses of each approach, and future technology directions.

show abstract

“…Malware analyses are a procedure that detects software programs to determine their behaviour, functioning and whether or not they are malware. Methods of Android malware detection may be classified or also dynamic analysis [9,10]. This indicates that every 10 seconds a new Android malware application is being identified, Malware detection technique may be classified as static detection, dynamic detection and hybrid detection in three categories [11,12].…”

Section: Introductionmentioning

confidence: 99%

A Comprehensive Study of Malware Detection in Android Operating Systems

Hamdi

Ibrahim

Omar

et al. 2021

AJRCoS

View full text Add to dashboard Cite

Android is now the world's (or one of the world’s) most popular operating system. More and more malware assaults are taking place in Android applications. Many security detection techniques based on Android Apps are now available. The open environmental feature of the Android environment has given Android an extensive appeal in recent years. The growing number of mobile devices are incorporated in many aspects of our everyday lives. This paper gives a detailed comparison that summarizes and analyses various detection techniques. This work examines the current status of Android malware detection methods, with an emphasis on Machine Learning-based classifiers for detecting malicious software on Android devices. Android has a huge number of apps that may be downloaded and used for free. Consequently, Android phones are more susceptible to malware. As a result, additional research has been done in order to develop effective malware detection methods. To begin, several of the currently available Android malware detection approaches are carefully examined and classified based on their detection methodologies. This study examines a wide range of machine-learning-based methods to detecting Android malware covering both types dynamic and static.

show abstract

Malware Detection in Android Systems with Traditional Machine Learning Models: A Survey

Cited by 24 publications

References 18 publications

Detecting Internet of Things Attacks by Using Hybrid Learning and Feature Selection Method

Detecting Internet of Things Attacks by Using Hybrid Learning and Feature Selection Method

A Survey of Android Malware Static Detection Technology Based on Machine Learning

A Comprehensive Study of Malware Detection in Android Operating Systems

Contact Info

Product

Resources

About