Abstract | ||
---|---|---|
Due to the open source and fragmentation of the Android system, its security is increasingly challenged. Currently, Android malware detection has certain deficiencies in large-scale and automation detection. In this paper, we proposed an Android malware detection framework based on Convolutional Neural Network (CNN). We used static analysis tools and python scripts to automatically extract 1003 static features, and transformed the features of each sample into a two-dimensional matrix as input to the CNN model. We selected 5000 malicious samples and 5000 benign samples for verification. The experimental results show that the detection accuracy of CNN reaches 99.68%, which is much higher than other algorithms.
|
Year | DOI | Venue |
---|---|---|
2019 | 10.1145/3331453.3361306 | Proceedings of the 3rd International Conference on Computer Science and Application Engineering |
Keywords | Field | DocType |
Android Static Analysis, Deep learning, Malware detection | Convolutional neural network,Computer science,Android malware,Artificial intelligence,Machine learning | Conference |
ISBN | Citations | PageRank |
978-1-4503-6294-8 | 0 | 0.34 |
References | Authors | |
0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhiqiang Wang | 1 | 158 | 35.98 |
Gefei Li | 2 | 0 | 0.68 |
Yaping Chi | 3 | 2 | 2.35 |
Jianyi Zhang | 4 | 2 | 2.01 |
Tao Yang | 5 | 160 | 76.32 |
Qixu Liu | 6 | 0 | 0.68 |