A Deep Learning-Based Approach for the Detection of Various Internet of Things Intrusion Attacks Through Optical Networks
The widespread use of the Internet of Things (IoT) has led to significant breakthroughs in various fields but has also exposed critical vulnerabilities to evolving cybersecurity threats. Current Intrusion Detection Systems (IDSs) often fail to provide real-time detection, scalability, and interpreta...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Photonics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2304-6732/12/1/35 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587662242873344 |
|---|---|
| author | Nouman Imtiaz Abdul Wahid Syed Zain Ul Abideen Mian Muhammad Kamal Nabila Sehito Salahuddin Khan Bal S. Virdee Lida Kouhalvandi Mohammad Alibakhshikenari |
| author_facet | Nouman Imtiaz Abdul Wahid Syed Zain Ul Abideen Mian Muhammad Kamal Nabila Sehito Salahuddin Khan Bal S. Virdee Lida Kouhalvandi Mohammad Alibakhshikenari |
| author_sort | Nouman Imtiaz |
| collection | DOAJ |
| description | The widespread use of the Internet of Things (IoT) has led to significant breakthroughs in various fields but has also exposed critical vulnerabilities to evolving cybersecurity threats. Current Intrusion Detection Systems (IDSs) often fail to provide real-time detection, scalability, and interpretability, particularly in high-speed optical network environments. This research introduces XIoT, which is a novel explainable IoT attack detection model designed to address these challenges. Leveraging advanced deep learning methods, specifically Convolutional Neural Networks (CNNs), XIoT analyzes spectrogram images transformed from IoT network traffic data to detect subtle and complex attack patterns. Unlike traditional approaches, XIoT emphasizes interpretability by integrating explainable AI mechanisms, enabling cybersecurity analysts to understand and trust its predictions. By offering actionable insights into the factors driving its decision making, XIoT supports informed responses to cyber threats. Furthermore, the model’s architecture leverages the high-speed, low-latency characteristics of optical networks, ensuring the efficient processing of large-scale IoT data streams and supporting real-time detection in diverse IoT ecosystems. Comprehensive experiments on benchmark datasets, including KDD CUP99, UNSW NB15, and Bot-IoT, demonstrate XIoT’s exceptional accuracy rates of 99.34%, 99.61%, and 99.21%, respectively, significantly surpassing existing methods in both accuracy and interpretability. These results highlight XIoT’s capability to enhance IoT security by addressing real-world challenges, ensuring robust, scalable, and interpretable protection for IoT networks against sophisticated cyber threats. |
| format | Article |
| id | doaj-art-a0a5daf5261c4bf59061d5c7585d1407 |
| institution | Kabale University |
| issn | 2304-6732 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Photonics |
| spelling | doaj-art-a0a5daf5261c4bf59061d5c7585d14072025-01-24T13:46:16ZengMDPI AGPhotonics2304-67322025-01-011213510.3390/photonics12010035A Deep Learning-Based Approach for the Detection of Various Internet of Things Intrusion Attacks Through Optical NetworksNouman Imtiaz0Abdul Wahid1Syed Zain Ul Abideen2Mian Muhammad Kamal3Nabila Sehito4Salahuddin Khan5Bal S. Virdee6Lida Kouhalvandi7Mohammad Alibakhshikenari8School of Computer Science and Technology, Shandong University, Qingdao 266510, ChinaCollege of Computer Science and Technology, Qingdao University, Qingdao 266071, ChinaCollege of Computer Science and Technology, Qingdao University, Qingdao 266071, ChinaSchool of Electronic Science and Engineering, Southeast University, No. 2 Southeast University Road, Jiangning, Nanjing 211189, ChinaDepartment of Computer Science, ILMA University, Karachi 74900, PakistanCollege of Engineering, King Saud University, P.O. Box 800, Riyadh 11421, Saudi ArabiaCenter for Communications Technology, London Metropolitan University, London N7 8DB, UKDepartment of Electrical and Electronics Engineering, Dogus University, Istanbul 34775, TurkeyElectronics Engineering Department, University of Rome “Tor Vergata”, 00133 Rome, ItalyThe widespread use of the Internet of Things (IoT) has led to significant breakthroughs in various fields but has also exposed critical vulnerabilities to evolving cybersecurity threats. Current Intrusion Detection Systems (IDSs) often fail to provide real-time detection, scalability, and interpretability, particularly in high-speed optical network environments. This research introduces XIoT, which is a novel explainable IoT attack detection model designed to address these challenges. Leveraging advanced deep learning methods, specifically Convolutional Neural Networks (CNNs), XIoT analyzes spectrogram images transformed from IoT network traffic data to detect subtle and complex attack patterns. Unlike traditional approaches, XIoT emphasizes interpretability by integrating explainable AI mechanisms, enabling cybersecurity analysts to understand and trust its predictions. By offering actionable insights into the factors driving its decision making, XIoT supports informed responses to cyber threats. Furthermore, the model’s architecture leverages the high-speed, low-latency characteristics of optical networks, ensuring the efficient processing of large-scale IoT data streams and supporting real-time detection in diverse IoT ecosystems. Comprehensive experiments on benchmark datasets, including KDD CUP99, UNSW NB15, and Bot-IoT, demonstrate XIoT’s exceptional accuracy rates of 99.34%, 99.61%, and 99.21%, respectively, significantly surpassing existing methods in both accuracy and interpretability. These results highlight XIoT’s capability to enhance IoT security by addressing real-world challenges, ensuring robust, scalable, and interpretable protection for IoT networks against sophisticated cyber threats.https://www.mdpi.com/2304-6732/12/1/35Internet of Thingsintrusion detection systemsdeep learningexplainable AIspectrogramnetwork attacks |
| spellingShingle | Nouman Imtiaz Abdul Wahid Syed Zain Ul Abideen Mian Muhammad Kamal Nabila Sehito Salahuddin Khan Bal S. Virdee Lida Kouhalvandi Mohammad Alibakhshikenari A Deep Learning-Based Approach for the Detection of Various Internet of Things Intrusion Attacks Through Optical Networks Photonics Internet of Things intrusion detection systems deep learning explainable AI spectrogram network attacks |
| title | A Deep Learning-Based Approach for the Detection of Various Internet of Things Intrusion Attacks Through Optical Networks |
| title_full | A Deep Learning-Based Approach for the Detection of Various Internet of Things Intrusion Attacks Through Optical Networks |
| title_fullStr | A Deep Learning-Based Approach for the Detection of Various Internet of Things Intrusion Attacks Through Optical Networks |
| title_full_unstemmed | A Deep Learning-Based Approach for the Detection of Various Internet of Things Intrusion Attacks Through Optical Networks |
| title_short | A Deep Learning-Based Approach for the Detection of Various Internet of Things Intrusion Attacks Through Optical Networks |
| title_sort | deep learning based approach for the detection of various internet of things intrusion attacks through optical networks |
| topic | Internet of Things intrusion detection systems deep learning explainable AI spectrogram network attacks |
| url | https://www.mdpi.com/2304-6732/12/1/35 |
| work_keys_str_mv | AT noumanimtiaz adeeplearningbasedapproachforthedetectionofvariousinternetofthingsintrusionattacksthroughopticalnetworks AT abdulwahid adeeplearningbasedapproachforthedetectionofvariousinternetofthingsintrusionattacksthroughopticalnetworks AT syedzainulabideen adeeplearningbasedapproachforthedetectionofvariousinternetofthingsintrusionattacksthroughopticalnetworks AT mianmuhammadkamal adeeplearningbasedapproachforthedetectionofvariousinternetofthingsintrusionattacksthroughopticalnetworks AT nabilasehito adeeplearningbasedapproachforthedetectionofvariousinternetofthingsintrusionattacksthroughopticalnetworks AT salahuddinkhan adeeplearningbasedapproachforthedetectionofvariousinternetofthingsintrusionattacksthroughopticalnetworks AT balsvirdee adeeplearningbasedapproachforthedetectionofvariousinternetofthingsintrusionattacksthroughopticalnetworks AT lidakouhalvandi adeeplearningbasedapproachforthedetectionofvariousinternetofthingsintrusionattacksthroughopticalnetworks AT mohammadalibakhshikenari adeeplearningbasedapproachforthedetectionofvariousinternetofthingsintrusionattacksthroughopticalnetworks AT noumanimtiaz deeplearningbasedapproachforthedetectionofvariousinternetofthingsintrusionattacksthroughopticalnetworks AT abdulwahid deeplearningbasedapproachforthedetectionofvariousinternetofthingsintrusionattacksthroughopticalnetworks AT syedzainulabideen deeplearningbasedapproachforthedetectionofvariousinternetofthingsintrusionattacksthroughopticalnetworks AT mianmuhammadkamal deeplearningbasedapproachforthedetectionofvariousinternetofthingsintrusionattacksthroughopticalnetworks AT nabilasehito deeplearningbasedapproachforthedetectionofvariousinternetofthingsintrusionattacksthroughopticalnetworks AT salahuddinkhan deeplearningbasedapproachforthedetectionofvariousinternetofthingsintrusionattacksthroughopticalnetworks AT balsvirdee deeplearningbasedapproachforthedetectionofvariousinternetofthingsintrusionattacksthroughopticalnetworks AT lidakouhalvandi deeplearningbasedapproachforthedetectionofvariousinternetofthingsintrusionattacksthroughopticalnetworks AT mohammadalibakhshikenari deeplearningbasedapproachforthedetectionofvariousinternetofthingsintrusionattacksthroughopticalnetworks |