Deep Learning Optimisation of Static Malware Detection with Grid Search and Covering Arrays
This paper investigates the impact of several hyperparameters on static malware detection using deep learning, including the number of epochs, batch size, number of layers and neurons, optimisation method, dropout rate, type of activation function, and learning rate. We employed the cAgen tool and g...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Telecom |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-4001/4/2/15 |
| _version_ | 1797592498549293056 |
|---|---|
| author | Fahad T. ALGorain Abdulrahman S. Alnaeem |
| author_facet | Fahad T. ALGorain Abdulrahman S. Alnaeem |
| author_sort | Fahad T. ALGorain |
| collection | DOAJ |
| description | This paper investigates the impact of several hyperparameters on static malware detection using deep learning, including the number of epochs, batch size, number of layers and neurons, optimisation method, dropout rate, type of activation function, and learning rate. We employed the cAgen tool and grid search optimisation from the scikit-learn Python library to identify the best hyperparameters for our Keras deep learning model. Our experiments reveal that cAgen is more efficient than grid search in finding the optimal parameters, and we find that the selection of hyperparameter values has a significant impact on the model’s accuracy. Specifically, our approach leads to significant improvements in the neural network model’s accuracy for static malware detection on the Ember dataset (from 81.2% to 95.7%) and the Kaggle dataset (from 94% to 98.6%). These results demonstrate the effectiveness of our proposed approach, and have important implications for the field of static malware detection. |
| first_indexed | 2024-03-11T01:51:59Z |
| format | Article |
| id | doaj.art-51ce30e6c458464694d4d84af4559390 |
| institution | Directory Open Access Journal |
| issn | 2673-4001 |
| language | English |
| last_indexed | 2024-03-11T01:51:59Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Telecom |
| spelling | doaj.art-51ce30e6c458464694d4d84af45593902023-11-18T12:53:16ZengMDPI AGTelecom2673-40012023-05-014224926410.3390/telecom4020015Deep Learning Optimisation of Static Malware Detection with Grid Search and Covering ArraysFahad T. ALGorain0Abdulrahman S. Alnaeem1Department of Computer Science, University of Sheffield, Sheffield S10 2TN, UKDepartment of Computer Science, University of Manchester, Manchester M13 9PL, UKThis paper investigates the impact of several hyperparameters on static malware detection using deep learning, including the number of epochs, batch size, number of layers and neurons, optimisation method, dropout rate, type of activation function, and learning rate. We employed the cAgen tool and grid search optimisation from the scikit-learn Python library to identify the best hyperparameters for our Keras deep learning model. Our experiments reveal that cAgen is more efficient than grid search in finding the optimal parameters, and we find that the selection of hyperparameter values has a significant impact on the model’s accuracy. Specifically, our approach leads to significant improvements in the neural network model’s accuracy for static malware detection on the Ember dataset (from 81.2% to 95.7%) and the Kaggle dataset (from 94% to 98.6%). These results demonstrate the effectiveness of our proposed approach, and have important implications for the field of static malware detection.https://www.mdpi.com/2673-4001/4/2/15hyperparameter optimisationstatic malware detectionneural networkdeep learninggrid searchcAgen |
| spellingShingle | Fahad T. ALGorain Abdulrahman S. Alnaeem Deep Learning Optimisation of Static Malware Detection with Grid Search and Covering Arrays Telecom hyperparameter optimisation static malware detection neural network deep learning grid search cAgen |
| title | Deep Learning Optimisation of Static Malware Detection with Grid Search and Covering Arrays |
| title_full | Deep Learning Optimisation of Static Malware Detection with Grid Search and Covering Arrays |
| title_fullStr | Deep Learning Optimisation of Static Malware Detection with Grid Search and Covering Arrays |
| title_full_unstemmed | Deep Learning Optimisation of Static Malware Detection with Grid Search and Covering Arrays |
| title_short | Deep Learning Optimisation of Static Malware Detection with Grid Search and Covering Arrays |
| title_sort | deep learning optimisation of static malware detection with grid search and covering arrays |
| topic | hyperparameter optimisation static malware detection neural network deep learning grid search cAgen |
| url | https://www.mdpi.com/2673-4001/4/2/15 |
| work_keys_str_mv | AT fahadtalgorain deeplearningoptimisationofstaticmalwaredetectionwithgridsearchandcoveringarrays AT abdulrahmansalnaeem deeplearningoptimisationofstaticmalwaredetectionwithgridsearchandcoveringarrays |