Explainable AI Assisted IoMT Security in Future 6G Networks
The rapid integration of the Internet of Medical Things (IoMT) is transforming healthcare through real-time monitoring, AI-driven diagnostics, and remote treatment. However, the growing reliance on IoMT devices, such as robotic surgical systems, life-support equipment, and wearable health monitors,...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Future Internet |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-5903/17/5/226 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849711174977847296 |
|---|---|
| author | Navneet Kaur Lav Gupta |
| author_facet | Navneet Kaur Lav Gupta |
| author_sort | Navneet Kaur |
| collection | DOAJ |
| description | The rapid integration of the Internet of Medical Things (IoMT) is transforming healthcare through real-time monitoring, AI-driven diagnostics, and remote treatment. However, the growing reliance on IoMT devices, such as robotic surgical systems, life-support equipment, and wearable health monitors, has expanded the attack surface, exposing healthcare systems to cybersecurity risks like data breaches, device manipulation, and potentially life-threatening disruptions. While 6G networks offer significant benefits for healthcare, such as ultra-low latency, extensive connectivity, and AI-native capabilities, as highlighted in the ITU 6G (IMT-2030) framework, they are expected to introduce new and potentially more severe security challenges. These advancements put critical medical systems at greater risk, highlighting the need for more robust security measures. This study leverages AI techniques to systematically identify security vulnerabilities within 6G-enabled healthcare environments. Additionally, the proposed approach strengthens AI-driven security through use of multiple XAI techniques cross-validated against each other. Drawing on the insights provided by XAI, we tailor our mitigation strategies to the ITU-defined 6G usage scenarios, with a focus on their applicability to medical IoT networks. We propose that these strategies will effectively address potential vulnerabilities and enhance the security of medical systems leveraging IoT and 6G networks. |
| format | Article |
| id | doaj-art-1b9773dcfd794a8db1332ac2f8435e8b |
| institution | DOAJ |
| issn | 1999-5903 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Future Internet |
| spelling | doaj-art-1b9773dcfd794a8db1332ac2f8435e8b2025-08-20T03:14:41ZengMDPI AGFuture Internet1999-59032025-05-0117522610.3390/fi17050226Explainable AI Assisted IoMT Security in Future 6G NetworksNavneet Kaur0Lav Gupta1Department of Computer Science, University of Missouri, St. Louis, MO 63121, USADepartment of Computer Science, University of Missouri, St. Louis, MO 63121, USAThe rapid integration of the Internet of Medical Things (IoMT) is transforming healthcare through real-time monitoring, AI-driven diagnostics, and remote treatment. However, the growing reliance on IoMT devices, such as robotic surgical systems, life-support equipment, and wearable health monitors, has expanded the attack surface, exposing healthcare systems to cybersecurity risks like data breaches, device manipulation, and potentially life-threatening disruptions. While 6G networks offer significant benefits for healthcare, such as ultra-low latency, extensive connectivity, and AI-native capabilities, as highlighted in the ITU 6G (IMT-2030) framework, they are expected to introduce new and potentially more severe security challenges. These advancements put critical medical systems at greater risk, highlighting the need for more robust security measures. This study leverages AI techniques to systematically identify security vulnerabilities within 6G-enabled healthcare environments. Additionally, the proposed approach strengthens AI-driven security through use of multiple XAI techniques cross-validated against each other. Drawing on the insights provided by XAI, we tailor our mitigation strategies to the ITU-defined 6G usage scenarios, with a focus on their applicability to medical IoT networks. We propose that these strategies will effectively address potential vulnerabilities and enhance the security of medical systems leveraging IoT and 6G networks.https://www.mdpi.com/1999-5903/17/5/226explainable AIartificial intelligenceSHAPLIMEDiCEcounterfactual explanations |
| spellingShingle | Navneet Kaur Lav Gupta Explainable AI Assisted IoMT Security in Future 6G Networks Future Internet explainable AI artificial intelligence SHAP LIME DiCE counterfactual explanations |
| title | Explainable AI Assisted IoMT Security in Future 6G Networks |
| title_full | Explainable AI Assisted IoMT Security in Future 6G Networks |
| title_fullStr | Explainable AI Assisted IoMT Security in Future 6G Networks |
| title_full_unstemmed | Explainable AI Assisted IoMT Security in Future 6G Networks |
| title_short | Explainable AI Assisted IoMT Security in Future 6G Networks |
| title_sort | explainable ai assisted iomt security in future 6g networks |
| topic | explainable AI artificial intelligence SHAP LIME DiCE counterfactual explanations |
| url | https://www.mdpi.com/1999-5903/17/5/226 |
| work_keys_str_mv | AT navneetkaur explainableaiassistediomtsecurityinfuture6gnetworks AT lavgupta explainableaiassistediomtsecurityinfuture6gnetworks |