2018
DOI: 10.3233/jifs-169424
|View full text |Cite
|
Sign up to set email alerts
|

Detecting Android malware using Long Short-term Memory (LSTM)

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
45
0

Year Published

2018
2018
2023
2023

Publication Types

Select...
5
4
1

Relationship

1
9

Authors

Journals

citations
Cited by 124 publications
(54 citation statements)
references
References 22 publications
0
45
0
Order By: Relevance
“…The proposed model is evaluated using 4208 apps and it achieves an accuracy of 95%. In [368], The effectiveness of RNN and LSTM models for detection of malware in android systems is studied. The models are evaluated using well-known datasets and it is found that the LSTM performs better than RNN.…”
Section: ) Deep Neural Network (Dnn)mentioning
confidence: 99%
“…The proposed model is evaluated using 4208 apps and it achieves an accuracy of 95%. In [368], The effectiveness of RNN and LSTM models for detection of malware in android systems is studied. The models are evaluated using well-known datasets and it is found that the LSTM performs better than RNN.…”
Section: ) Deep Neural Network (Dnn)mentioning
confidence: 99%
“…With the rapid development of the 3G/4G mobile Internet, a large number of malicious applications have emerged in the years [1], and they pose a great threat to the security of the Android platform [2]. The analysis and detection of Android malware has attracted widespread attention from academia and industry.…”
Section: Introductionmentioning
confidence: 99%
“…We implement the MTS trading strategy using the long short-term memory network (LSTM) and compare its performance to the pas-sive trading strategy. LSTMs are found usable in broad areas, such as sentence classification [2], trajectory prediction of autonomous vehicles [9], flood forecasting [8] and malware detection [15]. Furthermore, LSTM are used in engineering for estimating remaining useful life of systems [17] and in medicine for automated diagnosis of arrhythmia [11].…”
Section: Introductionmentioning
confidence: 99%