End-to-end malware detection for android IoT devices using deep learning

Ren, Zhongru; Wu, Huayue; Ning, Qian; Hussain, Iftikhar; Chen, Bingcai

doi:10.1016/j.adhoc.2020.102098

Cited by 108 publications

(44 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the data set containing 8K benign application and 8K malicious application, the DexCNN method can achieve 93.4% detection accuracy, and the DexCRNN method can achieve 95.8% detection accuracy. Simultaneously, both methods are not limited by the input file's size, do not need artificial feature engineering, and low resource consumption [23].…”

Section: A Malware Detection Using Deep Learning Based On Static Anamentioning

confidence: 99%

See 1 more Smart Citation

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: A Malware Detection Using Deep Learning Based On Static Anamentioning

confidence: 99%

“…In these papers, many detection models use a combination of various deep learning models for detection, such as CNN + LSTM [23], DAE + CNN [17], RNN + CNN [28]. Compared with the model using a deep learning model, the hybrid detection model can also achieve satisfactory results.…”

Section: Research Status Analysismentioning

confidence: 99%

Review of Android Malware Detection Based on Deep Learning

2020

View full text Add to dashboard Cite

show abstract

“…These features were then used for complex pattern and feature recogni-tion. Ren et al [6] used an end-to-end architecture to build deep learning models and characterize Android applications. Kolosnjaji et al [18] proposed the classification of malware system call sequences using convolution and recurrent network layers, in which the convolutional layer is used for feature extraction.…”

Section: Related Workmentioning

confidence: 99%

“…Mclaug et al [7] used the opcode call sequence as a feature input into the model. Ren et al [6] resampled the original bytecode of the Android application classes.dex file as an end-to-end Android malware detection method based on deep learning. The comparison of the methods shows that the proposed algorithm is superior over the previous research methods.…”

Section: ) Effect Of Test Set Distribution On Model Performancementioning

confidence: 99%

See 1 more Smart Citation

Malicious Code Detection Based on Code Semantic Features

2020

IEEE Access

View full text Add to dashboard Cite

With the development of smart phones, malicious applications for the Android platform have increased dramatically. The existing Android malicious code analysis methods majorly focus on detection based on signatures, inter-component communication, and other configuration information features. Such methods ignore the effect of the semantic features of the malicious code. Even a few such studies that exist are based on the statistical features of the code for malicious code detection. To address these shortcomings, we (1) use the code semantic structure features to reflect deep semantic information, (2) propose a preprocessing method of APK files to generate graphics that reflect the code semantic features, and (3) introduce the advanced graphical semantics for a graph convolutional network (GCN) model to automatically identify and learn semantics and extract features for malicious code detection. Experiments on a dataset confirm that the proposed method can achieve 95.8% detection accuracy. Compared with the existing methods that adopt configuration information features or statistical features of codes, our method shows higher accuracy.

show abstract

MUDROID: Android malware detection and classification based on permission and behavior for autonomous vehicles

Tang,

Da,

Wang

et al. 2023

Trans Emerging Tel Tech

View full text Add to dashboard Cite

With the growing popularity of autonomous vehicles, ensuring their safety has become a significant concern. Vehicle manufacturers have incorporated the Android operating system to enhance user convenience. However, the Android operating system's diversity and vulnerability may significantly impact autonomous vehicles because these natures lead to a critical threat in autonomous vehicle security: Android malware. The complex nature of multi‐data sources fusion in autonomous driving systems has resulted in low detection efficiency and accuracy for Android malware. Given the security requirements for autonomous‐driving systems, this article presents an Android malware classification method centered around the multifeature fusion and deep learning architecture designed to detect and classify Android malware within autonomous‐driving systems. The proposed MUDROID framework relies on the Android permission mechanism and behavioral feature to formulate a malware classification model. Comprising four essential components—feature extraction, representation, multifeature fusion, and classifier training, MUDROID leverages the advantages of CNN and GCN combination model and is adept at extracting and interpreting multidimensional features, consequently constructing a multifeature fusion classifier to amplify the efficiency and accuracy of Android malware detection and classification. The experiment results support MUDROID's superior classification performance, with an impressive Android malware detection accuracy rate of 98.69% and family classification (95.42%). The proposed method can detect and classify Android malware effectively, thus elevating the security and robustness of the self‐driving system. Additionally, the approach in this article also addresses feature representation issues in detecting malware variants, facilitating the recognition of Android malware variants across diverse platforms.

show abstract

End-to-end malware detection for android IoT devices using deep learning

Cited by 108 publications

References 6 publications

Review of Android Malware Detection Based on Deep Learning

Review of Android Malware Detection Based on Deep Learning

Malicious Code Detection Based on Code Semantic Features

MUDROID: Android malware detection and classification based on permission and behavior for autonomous vehicles

Contact Info

Product

Resources

About