Malware detection approach based on improved SOINN
To deal with the problems of dynamic update of detection model and high computation costs in malware detection model based on batch learning,a novel malware detection approach is proposed by combing SOINN and supervised classifiers,to reduce computation costs and enable the detection model to update...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
POSTS&TELECOM PRESS Co., LTD
2019-12-01
|
| Series: | 网络与信息安全学报 |
| Subjects: | |
| Online Access: | http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2019059 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841530085728845824 |
|---|---|
| author | Bin ZHANG Lixun LI Shuqin DONG |
| author_facet | Bin ZHANG Lixun LI Shuqin DONG |
| author_sort | Bin ZHANG |
| collection | DOAJ |
| description | To deal with the problems of dynamic update of detection model and high computation costs in malware detection model based on batch learning,a novel malware detection approach is proposed by combing SOINN and supervised classifiers,to reduce computation costs and enable the detection model to update dynamically with the assistance of SOINN′s incremental learning characteristic.Firstly,the improved SOINN was given.According to the whole alignment algorithm,search the adjusted weights of neurons under all input sequences in the learning cycle and then calculate the average value of all adjusted weights as the final result,to avoid SOINN′s stability under different input sequences and representativeness of original data,therefore improve malware detection accuracy.Then a data preprocessing algorithm was proposed based on nonnegative matrix factor and Z-score normalization to transfer the malware behavior feature vector from high dimension and high order to low dimension and low order,to speed up and avoid overfitting and further improve detection accuracy.The results of experiments show that proposed approach supports dynamic updating of detection model and has a significantly higher accuracy of detecting unknown new samples and lower computation costs than tradition methods. |
| format | Article |
| id | doaj-art-c76abe9d06a945db9d0c512eed42e36d |
| institution | Kabale University |
| issn | 2096-109X |
| language | English |
| publishDate | 2019-12-01 |
| publisher | POSTS&TELECOM PRESS Co., LTD |
| record_format | Article |
| series | 网络与信息安全学报 |
| spelling | doaj-art-c76abe9d06a945db9d0c512eed42e36d2025-01-15T03:13:48ZengPOSTS&TELECOM PRESS Co., LTD网络与信息安全学报2096-109X2019-12-015213059556872Malware detection approach based on improved SOINNBin ZHANGLixun LIShuqin DONGTo deal with the problems of dynamic update of detection model and high computation costs in malware detection model based on batch learning,a novel malware detection approach is proposed by combing SOINN and supervised classifiers,to reduce computation costs and enable the detection model to update dynamically with the assistance of SOINN′s incremental learning characteristic.Firstly,the improved SOINN was given.According to the whole alignment algorithm,search the adjusted weights of neurons under all input sequences in the learning cycle and then calculate the average value of all adjusted weights as the final result,to avoid SOINN′s stability under different input sequences and representativeness of original data,therefore improve malware detection accuracy.Then a data preprocessing algorithm was proposed based on nonnegative matrix factor and Z-score normalization to transfer the malware behavior feature vector from high dimension and high order to low dimension and low order,to speed up and avoid overfitting and further improve detection accuracy.The results of experiments show that proposed approach supports dynamic updating of detection model and has a significantly higher accuracy of detecting unknown new samples and lower computation costs than tradition methods.http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2019059SOINN algorithmmalware detectionneural networkincremental learningintrusion detection |
| spellingShingle | Bin ZHANG Lixun LI Shuqin DONG Malware detection approach based on improved SOINN 网络与信息安全学报 SOINN algorithm malware detection neural network incremental learning intrusion detection |
| title | Malware detection approach based on improved SOINN |
| title_full | Malware detection approach based on improved SOINN |
| title_fullStr | Malware detection approach based on improved SOINN |
| title_full_unstemmed | Malware detection approach based on improved SOINN |
| title_short | Malware detection approach based on improved SOINN |
| title_sort | malware detection approach based on improved soinn |
| topic | SOINN algorithm malware detection neural network incremental learning intrusion detection |
| url | http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2019059 |
| work_keys_str_mv | AT binzhang malwaredetectionapproachbasedonimprovedsoinn AT lixunli malwaredetectionapproachbasedonimprovedsoinn AT shuqindong malwaredetectionapproachbasedonimprovedsoinn |