Adversarial Drift Detection in Intrusion Detection System
The recent intrusion detection systems based on machine learning generally assume that the intrusion traffic always satisfies stationary of statistics.However,this assumption is not always held when adversaries arbitrarily alter the distribution of traffic data,or develop new attack techniques,which...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Beijing Xintong Media Co., Ltd
2015-03-01
|
| Series: | Dianxin kexue |
| Subjects: | |
| Online Access: | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2015058/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841529537442086912 |
|---|---|
| author | Yaguan Qian Xiaohui Guan |
| author_facet | Yaguan Qian Xiaohui Guan |
| author_sort | Yaguan Qian |
| collection | DOAJ |
| description | The recent intrusion detection systems based on machine learning generally assume that the intrusion traffic always satisfies stationary of statistics.However,this assumption is not always held when adversaries arbitrarily alter the distribution of traffic data,or develop new attack techniques,which may reduce the detection rate.To overcome this adversarial drift,a novel drift detection approach based on weighted Rényi distance was suggested.The experiment on KDD Cup99 shows that the weighted Rényi distance is able to perfectly detect the adversarial drift,and improve the intrusion detection rate by retraining the model. |
| format | Article |
| id | doaj-art-875cda1df9704f03b4f343be7aa26cc3 |
| institution | Kabale University |
| issn | 1000-0801 |
| language | zho |
| publishDate | 2015-03-01 |
| publisher | Beijing Xintong Media Co., Ltd |
| record_format | Article |
| series | Dianxin kexue |
| spelling | doaj-art-875cda1df9704f03b4f343be7aa26cc32025-01-15T03:17:25ZzhoBeijing Xintong Media Co., LtdDianxin kexue1000-08012015-03-0131677359615726Adversarial Drift Detection in Intrusion Detection SystemYaguan QianXiaohui GuanThe recent intrusion detection systems based on machine learning generally assume that the intrusion traffic always satisfies stationary of statistics.However,this assumption is not always held when adversaries arbitrarily alter the distribution of traffic data,or develop new attack techniques,which may reduce the detection rate.To overcome this adversarial drift,a novel drift detection approach based on weighted Rényi distance was suggested.The experiment on KDD Cup99 shows that the weighted Rényi distance is able to perfectly detect the adversarial drift,and improve the intrusion detection rate by retraining the model.http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2015058/intrusion detectionattack trafficadversarial driftweighted Rényi distance |
| spellingShingle | Yaguan Qian Xiaohui Guan Adversarial Drift Detection in Intrusion Detection System Dianxin kexue intrusion detection attack traffic adversarial drift weighted Rényi distance |
| title | Adversarial Drift Detection in Intrusion Detection System |
| title_full | Adversarial Drift Detection in Intrusion Detection System |
| title_fullStr | Adversarial Drift Detection in Intrusion Detection System |
| title_full_unstemmed | Adversarial Drift Detection in Intrusion Detection System |
| title_short | Adversarial Drift Detection in Intrusion Detection System |
| title_sort | adversarial drift detection in intrusion detection system |
| topic | intrusion detection attack traffic adversarial drift weighted Rényi distance |
| url | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2015058/ |
| work_keys_str_mv | AT yaguanqian adversarialdriftdetectioninintrusiondetectionsystem AT xiaohuiguan adversarialdriftdetectioninintrusiondetectionsystem |