CNN-Based Android Malware Detection

Ganesh, M. Jai; Pednekar, Priyanka; Prabhuswamy, Pooja; Nair, Divyashri Sreedharan; Park, Younghee; Jeon, Hyeran

doi:10.1109/icssa.2017.18

Cited by 54 publications

(41 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Meenu Ganesh et al [41] used static analysis to extract 138 permission features in four categories, converted the permission features into 12x12 PNG images, and used convolutional neural networks for model training and detection. In 2500 Android applications, it achieved 93% detection accuracy, including 2000 malicious samples and 500 benign samples.…”

Section: Malware Detection Using Deep Learning Based On Image Procmentioning

confidence: 99%

“…In [40]- [46], it is based on the image method combined with deep learning to detect Android malicious applications. In [40] [41], by converting the extracted features into images, using an imaging method to vectorize the features, the Android malware detection problem is converted into an image classification problem, and the neural network is trained by using image data. There are mature schemes for image classification using a convolutional neural network.…”

Section: Research Status Analysismentioning

confidence: 99%

“…Meenu Ganesh et al [41] used static analysis to extract 138 permission features. According to the number, the extracted permission features are numbered from 0 to 137 and then correspond to the PNG image pixel point's position number.…”

Section: Feature Vectorized Representationmentioning

confidence: 99%

See 2 more Smart Citations

Review of Android Malware Detection Based on Deep Learning

2020

View full text Add to dashboard Cite

At present, smartphones running the Android operating system have occupied the leading market share. However, due to the Android operating system's open-source nature, Android malware has increased dramatically. Malware can steal user privacy and even maliciously charge fees and steal funds. It has posed a severe threat to cyberspace security because traditional detection methods have many limitations. With the widespread application of deep learning in recent years, the method of detecting Android malware using deep learning has gradually attracted widespread attention from scholars at home and abroad. Although scholars have researched Android malware detection using deep learning, there is currently a lack of a detailed and comprehensive introduction to malware detection's latest research results based on deep learning. In order to solve this problem, this study analyzes and summarizes the latest research results by investigating a large number of the latest domestic and international academic papers, summarizing malware detection architecture and detection schemes, and analyzing existing problems and challenges. This review will help researchers better understand the research status and future research directions in this field. INDEX TERMS Android, malware, deep learning, review.

show abstract

Section: Malware Detection Using Deep Learning Based On Image Procmentioning

confidence: 99%

Section: Research Status Analysismentioning

confidence: 99%

See 1 more Smart Citation

Review of Android Malware Detection Based on Deep Learning

2020

View full text Add to dashboard Cite

show abstract

“…The LSTM is trained on permission sequence with bag-of-words embedding and optimal parameters and it achieves an accuracy of 89.7% on the realworld Android malware dataset, provided by CDMC2016. In [348], a CNN-based android malware detector is proposed. The framework extracts features from static analysis of android app permissions to build the CNN model.…”

Section: ) Deep Neural Network (Dnn)mentioning

confidence: 99%

A Comprehensive Tutorial and Survey of Applications of Deep Learning for Cyber Security

Ravi¹,

Alazab²,

Sriram³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Meenu Ganesh, et. al., [15] developed an android malware detection method which investigates permission patterns based on a convolutional neural network. The result shows the accuracy of 93% in identifying the malware apps among a set of 2000 malicious and 500 benign apps.…”

Section: Literature Surveymentioning

confidence: 99%

An Enhanced Method for Identifying Android Malware Detection

2019

IJRTE

View full text Add to dashboard Cite

In worldwide, all people are living with mobile applications for most of their life time. A statistical survey shows that mobile user exceeds 5 billions by 2019. There is a necessity to download different kinds of applications in different occasions. The library in android OS used for displaying media content has multiple vulnerabilities which enable the attackers to exploit media files and run the malicious code. The new ranges of attacks have been opened up today. The malware application does fraudulent activities automatically in the mobile without the knowledge of users. It is very difficult to identify the malware among such applications. Thus a challenge rises for protecting the mobile phones from these attacks. The existing method, “Significant Permission Identification for Machine-Learning-Based Android Malware Detection (SIGPID)”, which uses Multi-Level Data Pruning process to identify significant permissions. In SIGPID, three level pruning process namely Permission Ranking with Negative Rate (PRNR), Support based Permission Ranking (SPR) and Permission Mining with Association Rule (PMAR) are applied to the dataset followed by SVM classification. The large dimension of the dataset negatively affects the malware detection efficiency. To reduce features of malicious apps further, an enhanced method called “Enhanced Model of Significant Permission Identification (ESID)” is proposed to identify android malware applications using data mining techniques. It adds the process to remove non-significant permissions and to classify the benign apps and malicious apps using SVM before installing an android application in the mobile. The experimental result shows that the better accuracy of 93.75% in identifying the malicious apps..

show abstract

CNN-Based Android Malware Detection

Cited by 54 publications

References 9 publications

Review of Android Malware Detection Based on Deep Learning

Review of Android Malware Detection Based on Deep Learning

A Comprehensive Tutorial and Survey of Applications of Deep Learning for Cyber Security

An Enhanced Method for Identifying Android Malware Detection

Contact Info

Product

Resources

About