Permission based malware detection in android devices

Ilham, Soussi; Ghadi, Abderrahim; Abdelhakim, Boudhir Anouar

doi:10.1145/3286606.3286860

Cited by 16 publications

(11 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, since API calls can be manipulated, the classification of input samples may be incorrect. Ilham et al [1] and Yuan et al [17] proposed a deep learning-based extraction method of three types of features from the malware: (1) required permissions, (2) sensitive APIs, and (3) dynamic behavior. These features were then used for complex pattern and feature recogni-tion.…”

Section: Related Workmentioning

confidence: 99%

“…where k is the number of layers and 1) is the embedded matrix X composed of the embedded vectors corresponding to the nodes in the graph, W (k) is the weight matrix of the kth layer, and b (k) is the intercept of the kth layer. Specifically, N (v) is represented as a group of neighbors of node Ver, where Ver belongs to N (v) due to self-loops [24].…”

Section: B Malicious Code Detection Based On Deep Graph Convolutionamentioning

confidence: 99%

“…Many malware detection systems use static analysis techniques to detect malware. They mainly focus on the static features of malware, such as permissions required by the APK, services [1], sensitive application programming interface (API) [2], and program functions [3]. However, these features are only the information extracted from the config-uration file, ignoring the dex source code of the APK.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

Section: Related Workmentioning

confidence: 99%

Section: B Malicious Code Detection Based On Deep Graph Convolutionamentioning

confidence: 99%

Section: Introductionmentioning

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

show abstract

“…S. Ilham et al [3] proposed a system based on static analysis that follows permission-based technique. The procedure begins by first decompiling APK and then all or required application features are extracted from the source files which in the case are permissions from AndroidManifest.xml file.…”

Section: Related Workmentioning

confidence: 99%

“…The application is declared malicious based on its behavior checked while application is being executed. [3] A third technique is also popular and has proved to be more effective is formed by combining both static and dynamic techniques. An illustration of all three techniques is shown in Fig.…”

Section: Introductionmentioning

confidence: 99%

A Review of Hybrid Malware Detection Techniques in Android

Shabir

Sabahat

2020

2020 IEEE 23rd International Multitopic Conference (INMIC)

View full text Add to dashboard Cite

Android is one of the most popular mobile platforms with availability of thousands of applications on Play Store. These applications help us to be productive in our daily lives and now-a-days life without smartphones cannot be imagined. Unlike other platforms, Android's open source nature gives the developers a great leverage to create many applications with very few restrictions. This also attracts malware developers to target Android platform and since Android allows installing applications from unverified sources, the risk of installing an unwanted malware application arises which can compromise Android user's privacy and personal data. Some several tools and techniques that can detect these sorts of applications before or after installation and prevents loss of valuable data. In this paper, existing malware detection techniques are explored that use hybrid approach, compared, and contrasted in detail and a useful insight is presented for future research.

show abstract