A Robust Network Intrusion Detection System Using Random Forest Based Random Subspace Ensemble to Defend Against Adversarial Attacks
In recent years, machine learning (ML) has had a significant influence on the discipline of computer security. In network security, intrusion detection systems increasingly employ machine learning techniques. Approaches based on machine learning have substantially improved the efficacy of intrusio...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Stefan cel Mare University of Suceava
2023-11-01
|
| Series: | Advances in Electrical and Computer Engineering |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.4316/AECE.2023.04009 |
| _version_ | 1797289287108001792 |
|---|---|
| author | NATHANIEL, D. SOOSAI, A. |
| author_facet | NATHANIEL, D. SOOSAI, A. |
| author_sort | NATHANIEL, D. |
| collection | DOAJ |
| description | In recent years, machine learning (ML) has had a significant influence on the discipline of computer security. In network
security, intrusion detection systems increasingly employ machine learning techniques. Approaches based on machine learning
have substantially improved the efficacy of intrusion detection. Adaptive adversaries who comprehend the underlying
principles of ML techniques can initiate attacks against the classification engine of an intrusion detection system.
Malicious actors exploit machine learning model vulnerabilities. Network security, specifically intrusion detection
systems, requires the development of defensive strategies to combat this threat. The RF-RSE (Random Forest based
Random Subspace Ensemble) and RF-RSE-AT (RF-RSE-Adversarial Training) methods are proposed as network intrusion
detection systems to defend against adversarial attacks. The methodologies proposed are evaluated using the
NSL-KDD dataset. The RF-RSE method demonstrates remarkable resistance to adversary attacks. The RF-RSE-AT
method performs exceptionally well in correctly identifying network traffic classes when presented with
adversarial attacks, and it maintains its accuracy even when no attack is present. |
| first_indexed | 2024-03-07T19:02:45Z |
| format | Article |
| id | doaj.art-d08d41cba66c4e25a28607b413dc7763 |
| institution | Directory Open Access Journal |
| issn | 1582-7445 1844-7600 |
| language | English |
| last_indexed | 2024-03-07T19:02:45Z |
| publishDate | 2023-11-01 |
| publisher | Stefan cel Mare University of Suceava |
| record_format | Article |
| series | Advances in Electrical and Computer Engineering |
| spelling | doaj.art-d08d41cba66c4e25a28607b413dc77632024-03-01T12:55:34ZengStefan cel Mare University of SuceavaAdvances in Electrical and Computer Engineering1582-74451844-76002023-11-01234818810.4316/AECE.2023.04009A Robust Network Intrusion Detection System Using Random Forest Based Random Subspace Ensemble to Defend Against Adversarial AttacksNATHANIEL, D.SOOSAI, A.In recent years, machine learning (ML) has had a significant influence on the discipline of computer security. In network security, intrusion detection systems increasingly employ machine learning techniques. Approaches based on machine learning have substantially improved the efficacy of intrusion detection. Adaptive adversaries who comprehend the underlying principles of ML techniques can initiate attacks against the classification engine of an intrusion detection system. Malicious actors exploit machine learning model vulnerabilities. Network security, specifically intrusion detection systems, requires the development of defensive strategies to combat this threat. The RF-RSE (Random Forest based Random Subspace Ensemble) and RF-RSE-AT (RF-RSE-Adversarial Training) methods are proposed as network intrusion detection systems to defend against adversarial attacks. The methodologies proposed are evaluated using the NSL-KDD dataset. The RF-RSE method demonstrates remarkable resistance to adversary attacks. The RF-RSE-AT method performs exceptionally well in correctly identifying network traffic classes when presented with adversarial attacks, and it maintains its accuracy even when no attack is present.http://dx.doi.org/10.4316/AECE.2023.04009computer networkscomputer securitymachine learningfirewallsintrusion detection |
| spellingShingle | NATHANIEL, D. SOOSAI, A. A Robust Network Intrusion Detection System Using Random Forest Based Random Subspace Ensemble to Defend Against Adversarial Attacks Advances in Electrical and Computer Engineering computer networks computer security machine learning firewalls intrusion detection |
| title | A Robust Network Intrusion Detection System Using Random Forest Based Random Subspace Ensemble to Defend Against Adversarial Attacks |
| title_full | A Robust Network Intrusion Detection System Using Random Forest Based Random Subspace Ensemble to Defend Against Adversarial Attacks |
| title_fullStr | A Robust Network Intrusion Detection System Using Random Forest Based Random Subspace Ensemble to Defend Against Adversarial Attacks |
| title_full_unstemmed | A Robust Network Intrusion Detection System Using Random Forest Based Random Subspace Ensemble to Defend Against Adversarial Attacks |
| title_short | A Robust Network Intrusion Detection System Using Random Forest Based Random Subspace Ensemble to Defend Against Adversarial Attacks |
| title_sort | robust network intrusion detection system using random forest based random subspace ensemble to defend against adversarial attacks |
| topic | computer networks computer security machine learning firewalls intrusion detection |
| url | http://dx.doi.org/10.4316/AECE.2023.04009 |
| work_keys_str_mv | AT nathanield arobustnetworkintrusiondetectionsystemusingrandomforestbasedrandomsubspaceensembletodefendagainstadversarialattacks AT soosaia arobustnetworkintrusiondetectionsystemusingrandomforestbasedrandomsubspaceensembletodefendagainstadversarialattacks AT nathanield robustnetworkintrusiondetectionsystemusingrandomforestbasedrandomsubspaceensembletodefendagainstadversarialattacks AT soosaia robustnetworkintrusiondetectionsystemusingrandomforestbasedrandomsubspaceensembletodefendagainstadversarialattacks |