GAN Neural Networks Architectures for Testing Process Control Industrial Network Against Cyber-Attacks
Protection of computer systems and networks against malicious attacks is particularly important in industrial networked control systems. A successful cyber-attack may cause significant economic losses or even destruction of controlled processes. Therefore, it is necessary to test the vulnerability o...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10128113/ |
| _version_ | 1797818710976626688 |
|---|---|
| author | Krzysztof Zarzycki Patryk Chaber Krzysztof Cabaj Maciej Lawrynczuk Piotr Marusak Robert Nebeluk Sebastian Plamowski Andrzej Wojtulewicz |
| author_facet | Krzysztof Zarzycki Patryk Chaber Krzysztof Cabaj Maciej Lawrynczuk Piotr Marusak Robert Nebeluk Sebastian Plamowski Andrzej Wojtulewicz |
| author_sort | Krzysztof Zarzycki |
| collection | DOAJ |
| description | Protection of computer systems and networks against malicious attacks is particularly important in industrial networked control systems. A successful cyber-attack may cause significant economic losses or even destruction of controlled processes. Therefore, it is necessary to test the vulnerability of process control industrial networks against possible cyber-attacks. Three approaches employing Generative Adversarial Networks (GANs) to generate fake Modbus frames have been proposed in this work, tested for an industrial process control network and compared with the classical approach known from the literature. In the first approach, one GAN generates one byte of a message frame. In the next two approaches, expert knowledge about frame structure is used to generate a part of a message frame, while the remaining parts are generated using single or multiple GANs. The classical single-GAN approach is the worst one. The proposed one-GAN-per-byte approach generates significantly more correct message frames than the classical method. Moreover, all the generated fake frames have been correct in two of the proposed approaches, i.e., single GAN for selected bytes and multiple GANs for selected bytes methods. Finally, we describe the effect of cyber-attacks on the operation of the controlled process. |
| first_indexed | 2024-03-13T09:12:06Z |
| format | Article |
| id | doaj.art-52746cfd35144f4f9a19b86b7c5f5204 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-13T09:12:06Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-52746cfd35144f4f9a19b86b7c5f52042023-05-26T23:00:34ZengIEEEIEEE Access2169-35362023-01-0111495874960010.1109/ACCESS.2023.327725010128113GAN Neural Networks Architectures for Testing Process Control Industrial Network Against Cyber-AttacksKrzysztof Zarzycki0https://orcid.org/0000-0001-8436-7325Patryk Chaber1Krzysztof Cabaj2https://orcid.org/0000-0002-5955-5890Maciej Lawrynczuk3https://orcid.org/0000-0002-6846-2004Piotr Marusak4https://orcid.org/0000-0002-6556-7919Robert Nebeluk5Sebastian Plamowski6Andrzej Wojtulewicz7Faculty of Electronics and Information Technology, Institute of Control and Computation Engineering, Warsaw University of Technology, Warsaw, PolandFaculty of Electronics and Information Technology, Institute of Control and Computation Engineering, Warsaw University of Technology, Warsaw, PolandFaculty of Electronics and Information Technology, Institute of Computer Science, Warsaw University of Technology, Warsaw, PolandFaculty of Electronics and Information Technology, Institute of Control and Computation Engineering, Warsaw University of Technology, Warsaw, PolandFaculty of Electronics and Information Technology, Institute of Control and Computation Engineering, Warsaw University of Technology, Warsaw, PolandFaculty of Electronics and Information Technology, Institute of Control and Computation Engineering, Warsaw University of Technology, Warsaw, PolandFaculty of Electronics and Information Technology, Institute of Control and Computation Engineering, Warsaw University of Technology, Warsaw, PolandFaculty of Electronics and Information Technology, Institute of Control and Computation Engineering, Warsaw University of Technology, Warsaw, PolandProtection of computer systems and networks against malicious attacks is particularly important in industrial networked control systems. A successful cyber-attack may cause significant economic losses or even destruction of controlled processes. Therefore, it is necessary to test the vulnerability of process control industrial networks against possible cyber-attacks. Three approaches employing Generative Adversarial Networks (GANs) to generate fake Modbus frames have been proposed in this work, tested for an industrial process control network and compared with the classical approach known from the literature. In the first approach, one GAN generates one byte of a message frame. In the next two approaches, expert knowledge about frame structure is used to generate a part of a message frame, while the remaining parts are generated using single or multiple GANs. The classical single-GAN approach is the worst one. The proposed one-GAN-per-byte approach generates significantly more correct message frames than the classical method. Moreover, all the generated fake frames have been correct in two of the proposed approaches, i.e., single GAN for selected bytes and multiple GANs for selected bytes methods. Finally, we describe the effect of cyber-attacks on the operation of the controlled process.https://ieeexplore.ieee.org/document/10128113/GAN neural networkscyber-securitycyber-attacksindustrial network |
| spellingShingle | Krzysztof Zarzycki Patryk Chaber Krzysztof Cabaj Maciej Lawrynczuk Piotr Marusak Robert Nebeluk Sebastian Plamowski Andrzej Wojtulewicz GAN Neural Networks Architectures for Testing Process Control Industrial Network Against Cyber-Attacks IEEE Access GAN neural networks cyber-security cyber-attacks industrial network |
| title | GAN Neural Networks Architectures for Testing Process Control Industrial Network Against Cyber-Attacks |
| title_full | GAN Neural Networks Architectures for Testing Process Control Industrial Network Against Cyber-Attacks |
| title_fullStr | GAN Neural Networks Architectures for Testing Process Control Industrial Network Against Cyber-Attacks |
| title_full_unstemmed | GAN Neural Networks Architectures for Testing Process Control Industrial Network Against Cyber-Attacks |
| title_short | GAN Neural Networks Architectures for Testing Process Control Industrial Network Against Cyber-Attacks |
| title_sort | gan neural networks architectures for testing process control industrial network against cyber attacks |
| topic | GAN neural networks cyber-security cyber-attacks industrial network |
| url | https://ieeexplore.ieee.org/document/10128113/ |
| work_keys_str_mv | AT krzysztofzarzycki ganneuralnetworksarchitecturesfortestingprocesscontrolindustrialnetworkagainstcyberattacks AT patrykchaber ganneuralnetworksarchitecturesfortestingprocesscontrolindustrialnetworkagainstcyberattacks AT krzysztofcabaj ganneuralnetworksarchitecturesfortestingprocesscontrolindustrialnetworkagainstcyberattacks AT maciejlawrynczuk ganneuralnetworksarchitecturesfortestingprocesscontrolindustrialnetworkagainstcyberattacks AT piotrmarusak ganneuralnetworksarchitecturesfortestingprocesscontrolindustrialnetworkagainstcyberattacks AT robertnebeluk ganneuralnetworksarchitecturesfortestingprocesscontrolindustrialnetworkagainstcyberattacks AT sebastianplamowski ganneuralnetworksarchitecturesfortestingprocesscontrolindustrialnetworkagainstcyberattacks AT andrzejwojtulewicz ganneuralnetworksarchitecturesfortestingprocesscontrolindustrialnetworkagainstcyberattacks |