An Adversarial Approach for Intrusion Detection Systems Using Jacobian Saliency Map Attacks (JSMA) Algorithm
In today’s digital world, the information systems are revolutionizing the way we connect. As the people are trying to adopt and integrate intelligent systems into daily lives, the risks around cyberattacks on user-specific information have significantly grown. To ensure safe communication, the Intru...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-07-01
|
| Series: | Computers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-431X/9/3/58 |
| _version_ | 1797561858773745664 |
|---|---|
| author | Ayyaz Ul Haq Qureshi Hadi Larijani Mehdi Yousefi Ahsan Adeel Nhamoinesu Mtetwa |
| author_facet | Ayyaz Ul Haq Qureshi Hadi Larijani Mehdi Yousefi Ahsan Adeel Nhamoinesu Mtetwa |
| author_sort | Ayyaz Ul Haq Qureshi |
| collection | DOAJ |
| description | In today’s digital world, the information systems are revolutionizing the way we connect. As the people are trying to adopt and integrate intelligent systems into daily lives, the risks around cyberattacks on user-specific information have significantly grown. To ensure safe communication, the Intrusion Detection Systems (IDS) were developed often by using machine learning (ML) algorithms that have the unique ability to detect malware against network security violations. Recently, it was reported that the IDS are prone to carefully crafted perturbations known as adversaries. With the aim to understand the impact of such attacks, in this paper, we have proposed a novel random neural network-based adversarial intrusion detection system (RNN-ADV). The NSL-KDD dataset is utilized for training. For adversarial attack crafting, the Jacobian Saliency Map Attack (JSMA) algorithm is used, which identifies the feature which can cause maximum change to the benign samples with minimum added perturbation. To check the effectiveness of the proposed adversarial scheme, the results are compared with a deep neural network which indicates that RNN-ADV performs better in terms of accuracy, precision, recall, F1 score and training epochs. |
| first_indexed | 2024-03-10T18:20:33Z |
| format | Article |
| id | doaj.art-210d74c65db148bc9c65b3c50d21dfa0 |
| institution | Directory Open Access Journal |
| issn | 2073-431X |
| language | English |
| last_indexed | 2024-03-10T18:20:33Z |
| publishDate | 2020-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Computers |
| spelling | doaj.art-210d74c65db148bc9c65b3c50d21dfa02023-11-20T07:18:46ZengMDPI AGComputers2073-431X2020-07-01935810.3390/computers9030058An Adversarial Approach for Intrusion Detection Systems Using Jacobian Saliency Map Attacks (JSMA) AlgorithmAyyaz Ul Haq Qureshi0Hadi Larijani1Mehdi Yousefi2Ahsan Adeel3Nhamoinesu Mtetwa4School of Computing, Engineering and Built Environment, Glasgow Caledonian University, Glasgow G4 0BA, UKSchool of Computing, Engineering and Built Environment, Glasgow Caledonian University, Glasgow G4 0BA, UKSchool of Computing, Engineering and Built Environment, Glasgow Caledonian University, Glasgow G4 0BA, UKdeepCI.org, Edinburgh EH16 5XW, UKBarclays Bank Plc., Glasgow G2 7JT, UKIn today’s digital world, the information systems are revolutionizing the way we connect. As the people are trying to adopt and integrate intelligent systems into daily lives, the risks around cyberattacks on user-specific information have significantly grown. To ensure safe communication, the Intrusion Detection Systems (IDS) were developed often by using machine learning (ML) algorithms that have the unique ability to detect malware against network security violations. Recently, it was reported that the IDS are prone to carefully crafted perturbations known as adversaries. With the aim to understand the impact of such attacks, in this paper, we have proposed a novel random neural network-based adversarial intrusion detection system (RNN-ADV). The NSL-KDD dataset is utilized for training. For adversarial attack crafting, the Jacobian Saliency Map Attack (JSMA) algorithm is used, which identifies the feature which can cause maximum change to the benign samples with minimum added perturbation. To check the effectiveness of the proposed adversarial scheme, the results are compared with a deep neural network which indicates that RNN-ADV performs better in terms of accuracy, precision, recall, F1 score and training epochs.https://www.mdpi.com/2073-431X/9/3/58intrusion detectionadversarial attacksJSMANSL-KDDnetwork security |
| spellingShingle | Ayyaz Ul Haq Qureshi Hadi Larijani Mehdi Yousefi Ahsan Adeel Nhamoinesu Mtetwa An Adversarial Approach for Intrusion Detection Systems Using Jacobian Saliency Map Attacks (JSMA) Algorithm Computers intrusion detection adversarial attacks JSMA NSL-KDD network security |
| title | An Adversarial Approach for Intrusion Detection Systems Using Jacobian Saliency Map Attacks (JSMA) Algorithm |
| title_full | An Adversarial Approach for Intrusion Detection Systems Using Jacobian Saliency Map Attacks (JSMA) Algorithm |
| title_fullStr | An Adversarial Approach for Intrusion Detection Systems Using Jacobian Saliency Map Attacks (JSMA) Algorithm |
| title_full_unstemmed | An Adversarial Approach for Intrusion Detection Systems Using Jacobian Saliency Map Attacks (JSMA) Algorithm |
| title_short | An Adversarial Approach for Intrusion Detection Systems Using Jacobian Saliency Map Attacks (JSMA) Algorithm |
| title_sort | adversarial approach for intrusion detection systems using jacobian saliency map attacks jsma algorithm |
| topic | intrusion detection adversarial attacks JSMA NSL-KDD network security |
| url | https://www.mdpi.com/2073-431X/9/3/58 |
| work_keys_str_mv | AT ayyazulhaqqureshi anadversarialapproachforintrusiondetectionsystemsusingjacobiansaliencymapattacksjsmaalgorithm AT hadilarijani anadversarialapproachforintrusiondetectionsystemsusingjacobiansaliencymapattacksjsmaalgorithm AT mehdiyousefi anadversarialapproachforintrusiondetectionsystemsusingjacobiansaliencymapattacksjsmaalgorithm AT ahsanadeel anadversarialapproachforintrusiondetectionsystemsusingjacobiansaliencymapattacksjsmaalgorithm AT nhamoinesumtetwa anadversarialapproachforintrusiondetectionsystemsusingjacobiansaliencymapattacksjsmaalgorithm AT ayyazulhaqqureshi adversarialapproachforintrusiondetectionsystemsusingjacobiansaliencymapattacksjsmaalgorithm AT hadilarijani adversarialapproachforintrusiondetectionsystemsusingjacobiansaliencymapattacksjsmaalgorithm AT mehdiyousefi adversarialapproachforintrusiondetectionsystemsusingjacobiansaliencymapattacksjsmaalgorithm AT ahsanadeel adversarialapproachforintrusiondetectionsystemsusingjacobiansaliencymapattacksjsmaalgorithm AT nhamoinesumtetwa adversarialapproachforintrusiondetectionsystemsusingjacobiansaliencymapattacksjsmaalgorithm |