APT Adversarial Defence Mechanism for Industrial IoT Enabled Cyber-Physical System
The objective of Advanced Persistent Threat (APT) attacks is to exploit Cyber-Physical Systems (CPSs) in combination with the Industrial Internet of Things (I-IoT) by using fast attack methods. Machine learning (ML) techniques have shown potential in identifying APT attacks in autonomous and malware...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10171354/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832582419877724160 |
|---|---|
| author | Safdar Hussain Javed Maaz Bin Ahmad Muhammad Asif Waseem Akram Khalid Mahmood Ashok Kumar Das Sachin Shetty |
| author_facet | Safdar Hussain Javed Maaz Bin Ahmad Muhammad Asif Waseem Akram Khalid Mahmood Ashok Kumar Das Sachin Shetty |
| author_sort | Safdar Hussain Javed |
| collection | DOAJ |
| description | The objective of Advanced Persistent Threat (APT) attacks is to exploit Cyber-Physical Systems (CPSs) in combination with the Industrial Internet of Things (I-IoT) by using fast attack methods. Machine learning (ML) techniques have shown potential in identifying APT attacks in autonomous and malware detection systems. However, detecting hidden APT attacks in the I-IoT-enabled CPS domain and achieving real-time accuracy in detection present significant challenges for these techniques. To overcome these issues, a new approach is suggested that is based on the Graph Attention Network (GAN), a multi-dimensional algorithm that captures behavioral features along with the relevant information that other methods do not deliver. This approach utilizes masked self-attentional layers to address the limitations of prior Deep Learning (DL) methods that rely on convolutions. Two datasets, the DAPT2020 malware, and Edge I-IoT datasets are used to evaluate the approach, and it attains the highest detection accuracy of 96.97% and 95.97%, with prediction time of 20.56 seconds and 21.65 seconds, respectively. The GAN approach is compared to conventional ML algorithms, and simulation results demonstrate a significant performance improvement over these algorithms in the I-IoT-enabled CPS realm. |
| format | Article |
| id | doaj-art-fd808c29ee9e42858fa8dd7ee4dab98b |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-fd808c29ee9e42858fa8dd7ee4dab98b2025-01-30T00:00:24ZengIEEEIEEE Access2169-35362023-01-0111740007402010.1109/ACCESS.2023.329159910171354APT Adversarial Defence Mechanism for Industrial IoT Enabled Cyber-Physical SystemSafdar Hussain Javed0Maaz Bin Ahmad1https://orcid.org/0000-0001-9269-3374Muhammad Asif2https://orcid.org/0000-0001-6811-0044Waseem Akram3Khalid Mahmood4https://orcid.org/0000-0001-5046-7766Ashok Kumar Das5https://orcid.org/0000-0002-5196-9589Sachin Shetty6https://orcid.org/0000-0002-8789-0610College of Computing and Information Sciences, Karachi Institute of Economics and Technology (KIET), Karachi, PakistanCollege of Computing and Information Sciences, Karachi Institute of Economics and Technology (KIET), Karachi, PakistanDepartment of Computer Science, Lahore Garrison University, Lahore, PakistanDepartment of Computer Science, Lahore Garrison University, Lahore, PakistanGraduate School of Intelligent Data Science, National Yunlin University of Science and Technology, Douliu, TaiwanCenter for Security, Theory and Algorithmic Research, International Institute of Information Technology at Hyderabad, Hyderabad, IndiaDepartment of Modeling, Simulation and Visualization Engineering, Virginia Modeling, Analysis and Simulation Center, Old Dominion University, Suffolk, VA, USAThe objective of Advanced Persistent Threat (APT) attacks is to exploit Cyber-Physical Systems (CPSs) in combination with the Industrial Internet of Things (I-IoT) by using fast attack methods. Machine learning (ML) techniques have shown potential in identifying APT attacks in autonomous and malware detection systems. However, detecting hidden APT attacks in the I-IoT-enabled CPS domain and achieving real-time accuracy in detection present significant challenges for these techniques. To overcome these issues, a new approach is suggested that is based on the Graph Attention Network (GAN), a multi-dimensional algorithm that captures behavioral features along with the relevant information that other methods do not deliver. This approach utilizes masked self-attentional layers to address the limitations of prior Deep Learning (DL) methods that rely on convolutions. Two datasets, the DAPT2020 malware, and Edge I-IoT datasets are used to evaluate the approach, and it attains the highest detection accuracy of 96.97% and 95.97%, with prediction time of 20.56 seconds and 21.65 seconds, respectively. The GAN approach is compared to conventional ML algorithms, and simulation results demonstrate a significant performance improvement over these algorithms in the I-IoT-enabled CPS realm.https://ieeexplore.ieee.org/document/10171354/Advanced persistent threatdeep learningcyber-physical systemsgraph attention networksgraph neural networksthe Industrial Internet of Things |
| spellingShingle | Safdar Hussain Javed Maaz Bin Ahmad Muhammad Asif Waseem Akram Khalid Mahmood Ashok Kumar Das Sachin Shetty APT Adversarial Defence Mechanism for Industrial IoT Enabled Cyber-Physical System IEEE Access Advanced persistent threat deep learning cyber-physical systems graph attention networks graph neural networks the Industrial Internet of Things |
| title | APT Adversarial Defence Mechanism for Industrial IoT Enabled Cyber-Physical System |
| title_full | APT Adversarial Defence Mechanism for Industrial IoT Enabled Cyber-Physical System |
| title_fullStr | APT Adversarial Defence Mechanism for Industrial IoT Enabled Cyber-Physical System |
| title_full_unstemmed | APT Adversarial Defence Mechanism for Industrial IoT Enabled Cyber-Physical System |
| title_short | APT Adversarial Defence Mechanism for Industrial IoT Enabled Cyber-Physical System |
| title_sort | apt adversarial defence mechanism for industrial iot enabled cyber physical system |
| topic | Advanced persistent threat deep learning cyber-physical systems graph attention networks graph neural networks the Industrial Internet of Things |
| url | https://ieeexplore.ieee.org/document/10171354/ |
| work_keys_str_mv | AT safdarhussainjaved aptadversarialdefencemechanismforindustrialiotenabledcyberphysicalsystem AT maazbinahmad aptadversarialdefencemechanismforindustrialiotenabledcyberphysicalsystem AT muhammadasif aptadversarialdefencemechanismforindustrialiotenabledcyberphysicalsystem AT waseemakram aptadversarialdefencemechanismforindustrialiotenabledcyberphysicalsystem AT khalidmahmood aptadversarialdefencemechanismforindustrialiotenabledcyberphysicalsystem AT ashokkumardas aptadversarialdefencemechanismforindustrialiotenabledcyberphysicalsystem AT sachinshetty aptadversarialdefencemechanismforindustrialiotenabledcyberphysicalsystem |