Method based on contrastive learning for fine-grained unknown malicious traffic classification
In order to protect against unknown threats and evasion attacks, a new method based on contrastive learning for fine-grained unknown malicious traffic classification was proposed.Specifically, based on variational auto-encoder (CVAE), it included two classification stages, and cross entropy and reco...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2022-10-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2022180/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841539951864315904 |
|---|---|
| author | Yifeng WANG Yuanbo GUO Qingli CHEN Chen FANG Renhao LIN |
| author_facet | Yifeng WANG Yuanbo GUO Qingli CHEN Chen FANG Renhao LIN |
| author_sort | Yifeng WANG |
| collection | DOAJ |
| description | In order to protect against unknown threats and evasion attacks, a new method based on contrastive learning for fine-grained unknown malicious traffic classification was proposed.Specifically, based on variational auto-encoder (CVAE), it included two classification stages, and cross entropy and reconstruction errors were used for known and unknown traffic classification respectively.Different form other methods, contrastive learning was adopted in different classification stages, which significantly improved the classification performance of the few-shot and unknown (zero-shot) classes.Moreover, some techniques (e.g., re-training and re-sample) combined with contrastive learning further improved the classification performance of the few-shot classes and the generalization ability of model.Experimental results indicate that the proposed method has increased the macro recall of few-shot classes by 20.3% and the recall of unknown attacks by 9.1% respectively, and it also has protected against evasion attacks on partial classes to some extent. |
| format | Article |
| id | doaj-art-029ddfad0e904785b24d60e86c6861cb |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2022-10-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-029ddfad0e904785b24d60e86c6861cb2025-01-14T06:29:59ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2022-10-0143122559395985Method based on contrastive learning for fine-grained unknown malicious traffic classificationYifeng WANGYuanbo GUOQingli CHENChen FANGRenhao LINIn order to protect against unknown threats and evasion attacks, a new method based on contrastive learning for fine-grained unknown malicious traffic classification was proposed.Specifically, based on variational auto-encoder (CVAE), it included two classification stages, and cross entropy and reconstruction errors were used for known and unknown traffic classification respectively.Different form other methods, contrastive learning was adopted in different classification stages, which significantly improved the classification performance of the few-shot and unknown (zero-shot) classes.Moreover, some techniques (e.g., re-training and re-sample) combined with contrastive learning further improved the classification performance of the few-shot classes and the generalization ability of model.Experimental results indicate that the proposed method has increased the macro recall of few-shot classes by 20.3% and the recall of unknown attacks by 9.1% respectively, and it also has protected against evasion attacks on partial classes to some extent.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2022180/networA traffic classificationcontrastive learningvariational auto-encoderintrusion detection |
| spellingShingle | Yifeng WANG Yuanbo GUO Qingli CHEN Chen FANG Renhao LIN Method based on contrastive learning for fine-grained unknown malicious traffic classification Tongxin xuebao networA traffic classification contrastive learning variational auto-encoder intrusion detection |
| title | Method based on contrastive learning for fine-grained unknown malicious traffic classification |
| title_full | Method based on contrastive learning for fine-grained unknown malicious traffic classification |
| title_fullStr | Method based on contrastive learning for fine-grained unknown malicious traffic classification |
| title_full_unstemmed | Method based on contrastive learning for fine-grained unknown malicious traffic classification |
| title_short | Method based on contrastive learning for fine-grained unknown malicious traffic classification |
| title_sort | method based on contrastive learning for fine grained unknown malicious traffic classification |
| topic | networA traffic classification contrastive learning variational auto-encoder intrusion detection |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2022180/ |
| work_keys_str_mv | AT yifengwang methodbasedoncontrastivelearningforfinegrainedunknownmalicioustrafficclassification AT yuanboguo methodbasedoncontrastivelearningforfinegrainedunknownmalicioustrafficclassification AT qinglichen methodbasedoncontrastivelearningforfinegrainedunknownmalicioustrafficclassification AT chenfang methodbasedoncontrastivelearningforfinegrainedunknownmalicioustrafficclassification AT renhaolin methodbasedoncontrastivelearningforfinegrainedunknownmalicioustrafficclassification |