An intelligent intrusion detection system for cyber-physical systems using GAN-LSTM networks
Cyber-Physical Systems (CPS) face increasing cybersecurity threats, demanding advanced intrusion detection methods. This research proposes a novel GAN-LSTM hybrid model to enhance anomaly detection in CPS by addressing key limitations of traditional approaches, including class imbalance and temporal...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-06-01
|
| Series: | Franklin Open |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2773186325000714 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849423672622710784 |
|---|---|
| author | Md Shakil Siddique Md. Ashikur Rahman Khan Ishtiaq Ahammad Nishu Nath Joysri Rani Das Fardowsi Rahman |
| author_facet | Md Shakil Siddique Md. Ashikur Rahman Khan Ishtiaq Ahammad Nishu Nath Joysri Rani Das Fardowsi Rahman |
| author_sort | Md Shakil Siddique |
| collection | DOAJ |
| description | Cyber-Physical Systems (CPS) face increasing cybersecurity threats, demanding advanced intrusion detection methods. This research proposes a novel GAN-LSTM hybrid model to enhance anomaly detection in CPS by addressing key limitations of traditional approaches, including class imbalance and temporal dependency learning. The primary objectives are: (i) developing an adversarial learning framework where the generator synthesizes realistic attack patterns while the discriminator improves detection robustness, (ii) introducing a hybrid anomaly scoring mechanism combining reconstruction and discrimination loss, and (iii) validating performance on real-world CPS datasets (SWaT and WADI). The model achieves 87 % accuracy (SWaT) and 91 % accuracy (WADI), with precision reaching 93 % (SWaT) and 97 % (WADI)—demonstrating strong capability to minimize false alarms. Notably, it attains 99 % recall on SWaT, ensuring near-complete attack detection, though WADI recall remains lower (75 %) due to complex attack patterns. The balanced F1-scores (91 % SWaT, 82 % WADI) outperform state-of-the-art methods like MAD-GAN by 14–45 %. Key innovations include LSTM-based temporal feature learning and GAN-driven synthetic minority oversampling, effectively handling CPS-specific challenges such as multivariate time-series complexity and rare attack instances. These results highlight the model’s potential for real-world CPS security, while future work will address deployment constraints like computational latency. |
| format | Article |
| id | doaj-art-85a45c76d075424d885eb7a61a768c2b |
| institution | Kabale University |
| issn | 2773-1863 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Franklin Open |
| spelling | doaj-art-85a45c76d075424d885eb7a61a768c2b2025-08-20T03:30:32ZengElsevierFranklin Open2773-18632025-06-011110028110.1016/j.fraope.2025.100281An intelligent intrusion detection system for cyber-physical systems using GAN-LSTM networksMd Shakil Siddique0Md. Ashikur Rahman Khan1Ishtiaq Ahammad2Nishu Nath3Joysri Rani Das4Fardowsi Rahman5Department of Information and Communication Engineering, Noakhali Science and Technology University, Noakhali 3814, BangladeshDepartment of Information and Communication Engineering, Noakhali Science and Technology University, Noakhali 3814, Bangladesh; Corresponding author.Department of Computer Science and Engineering, Northern University Bangladesh, Dhaka 1230, BangladeshDepartment of Information and Communication Engineering, Noakhali Science and Technology University, Noakhali 3814, BangladeshDepartment of Information and Communication Engineering, Noakhali Science and Technology University, Noakhali 3814, BangladeshDepartment of Computer Science and Engineering, Primeasia University, Dhaka 1213, BangladeshCyber-Physical Systems (CPS) face increasing cybersecurity threats, demanding advanced intrusion detection methods. This research proposes a novel GAN-LSTM hybrid model to enhance anomaly detection in CPS by addressing key limitations of traditional approaches, including class imbalance and temporal dependency learning. The primary objectives are: (i) developing an adversarial learning framework where the generator synthesizes realistic attack patterns while the discriminator improves detection robustness, (ii) introducing a hybrid anomaly scoring mechanism combining reconstruction and discrimination loss, and (iii) validating performance on real-world CPS datasets (SWaT and WADI). The model achieves 87 % accuracy (SWaT) and 91 % accuracy (WADI), with precision reaching 93 % (SWaT) and 97 % (WADI)—demonstrating strong capability to minimize false alarms. Notably, it attains 99 % recall on SWaT, ensuring near-complete attack detection, though WADI recall remains lower (75 %) due to complex attack patterns. The balanced F1-scores (91 % SWaT, 82 % WADI) outperform state-of-the-art methods like MAD-GAN by 14–45 %. Key innovations include LSTM-based temporal feature learning and GAN-driven synthetic minority oversampling, effectively handling CPS-specific challenges such as multivariate time-series complexity and rare attack instances. These results highlight the model’s potential for real-world CPS security, while future work will address deployment constraints like computational latency.http://www.sciencedirect.com/science/article/pii/S2773186325000714Intrusion Detection System (IDS)Generative Adversarial Networks (GANs)Long short-term memory (LSTM)Anomaly detectionCybersecurityCyber-Physical Systems (CPSs) |
| spellingShingle | Md Shakil Siddique Md. Ashikur Rahman Khan Ishtiaq Ahammad Nishu Nath Joysri Rani Das Fardowsi Rahman An intelligent intrusion detection system for cyber-physical systems using GAN-LSTM networks Franklin Open Intrusion Detection System (IDS) Generative Adversarial Networks (GANs) Long short-term memory (LSTM) Anomaly detection Cybersecurity Cyber-Physical Systems (CPSs) |
| title | An intelligent intrusion detection system for cyber-physical systems using GAN-LSTM networks |
| title_full | An intelligent intrusion detection system for cyber-physical systems using GAN-LSTM networks |
| title_fullStr | An intelligent intrusion detection system for cyber-physical systems using GAN-LSTM networks |
| title_full_unstemmed | An intelligent intrusion detection system for cyber-physical systems using GAN-LSTM networks |
| title_short | An intelligent intrusion detection system for cyber-physical systems using GAN-LSTM networks |
| title_sort | intelligent intrusion detection system for cyber physical systems using gan lstm networks |
| topic | Intrusion Detection System (IDS) Generative Adversarial Networks (GANs) Long short-term memory (LSTM) Anomaly detection Cybersecurity Cyber-Physical Systems (CPSs) |
| url | http://www.sciencedirect.com/science/article/pii/S2773186325000714 |
| work_keys_str_mv | AT mdshakilsiddique anintelligentintrusiondetectionsystemforcyberphysicalsystemsusingganlstmnetworks AT mdashikurrahmankhan anintelligentintrusiondetectionsystemforcyberphysicalsystemsusingganlstmnetworks AT ishtiaqahammad anintelligentintrusiondetectionsystemforcyberphysicalsystemsusingganlstmnetworks AT nishunath anintelligentintrusiondetectionsystemforcyberphysicalsystemsusingganlstmnetworks AT joysriranidas anintelligentintrusiondetectionsystemforcyberphysicalsystemsusingganlstmnetworks AT fardowsirahman anintelligentintrusiondetectionsystemforcyberphysicalsystemsusingganlstmnetworks AT mdshakilsiddique intelligentintrusiondetectionsystemforcyberphysicalsystemsusingganlstmnetworks AT mdashikurrahmankhan intelligentintrusiondetectionsystemforcyberphysicalsystemsusingganlstmnetworks AT ishtiaqahammad intelligentintrusiondetectionsystemforcyberphysicalsystemsusingganlstmnetworks AT nishunath intelligentintrusiondetectionsystemforcyberphysicalsystemsusingganlstmnetworks AT joysriranidas intelligentintrusiondetectionsystemforcyberphysicalsystemsusingganlstmnetworks AT fardowsirahman intelligentintrusiondetectionsystemforcyberphysicalsystemsusingganlstmnetworks |