2018 IEEE 18th International Conference on Communication Technology (ICCT) 2018
DOI: 10.1109/icct.2018.8600052
|View full text |Cite
|
Sign up to set email alerts
|

Deep Neural Network Based on Android Mobile Malware Detection System Using Opcode Sequences

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
20
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
3
2
1

Relationship

1
5

Authors

Journals

citations
Cited by 22 publications
(20 citation statements)
references
References 12 publications
0
20
0
Order By: Relevance
“…Additionally, in Ref. [120], a one-dimensional feature vector is converted into a two-dimensional matrix to facilitate deep neural network learning.…”
Section: ) Data Preprocessingmentioning
confidence: 99%
See 3 more Smart Citations
“…Additionally, in Ref. [120], a one-dimensional feature vector is converted into a two-dimensional matrix to facilitate deep neural network learning.…”
Section: ) Data Preprocessingmentioning
confidence: 99%
“…The co-occurrence matrix is established based on the system call sequence and is then normalized and finally transformed into a vector. [120] Researchers convert the opcode sequence into a matrix vector, and transform the one-dimensional vector into a two-dimensional matrix, which is suitable for subsequent learning in a deep neural network (DNN). [121] The function call graphs (FCGs) extracted from an APK file are used to generate the topological signatures of the corresponding applications.…”
Section: ) Feature Selectionmentioning
confidence: 99%
See 2 more Smart Citations
“…The model is trained using smali files from 50 apks and it outperforms traditional ML models with an AUC of 85.98% and 70% in both WPDP and CPDP mode respectively. In [371], a CNN based android malware detection framework is presented. The model uses opcode sequences from decompiled apk files to learn to differentiate between malicious and benign apps.…”
Section: ) Deep Neural Network (Dnn)mentioning
confidence: 99%