The DOI matches its Crossref record.
Enhancing loMT Security with Deep Learning Based Approach for Medical IoT Threat Detection
Abstract
The rapid spread of Internet of Medical Things (IoMT) systems makes the security of these systems critical. Although IoMT can improve patient care and optimize health care services, it also poses cyberattacks and data breaches. In this context, securing IoMT systems is important for patient privacy and system integrity. A deep learning-based approach is proposed in this study to detect cyberattacks that may occur in IoMT systems. Deep Neural Networks (DNN) and Long-Short Term Memory (LSTM) architectures are used on the CICIoMT2024 dataset. An Fl-score of 99% was achieved for binary classification and over 75% for categorical and multiclass classification tasks. In particular, the LSTM architecture exhibited high performance in detecting complex attack patterns. The experimental results provide new insights for future research and provide effective and scalable solutions to improve the security of IoMT systems.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“On the IoMT side, stacking ensembles and CNN+LSTM hybrids on CICIoMT2024 reach binary, categorical, and multiclass accuracies near 99% [114,131-133].”
From Agentic AI and Large Language Models for Autonomous IoT Cybersecurity: A Systematic Survey, Taxonomy, and Research Roadmap (2026) · cites this paper as [131]
Citations
Cites
Still being checked.
Cited by
Sorted by citations
Tawfik, M., Abu-Ein, A. A.-K. H., Noaman, H. M., Abdelhaliem, A. H., & Fathi, I. S. (2025) · Scientific Reports · doi:10.1038/s41598-025-25107-z · Cited by 32
Kouassi, B. M., Ballo, A. B., Ayikpa, K. J., Mamadou, D., & Coulibaly, M. Z. J. (2025) · Future Internet · doi:10.3390/fi17110529 · Cited by 26
Nnadiekwe, C. A., Ajakwe, S. O., Lee, J.-M., & Kim, D.-S. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3633505 · Cited by 10
Nageshwaran, V., & Ezekiel, S. (2026) · Electronics · doi:10.3390/electronics15122740 · Cited by 4
“At the perception/network boundary, line-rate non-LLM detectors trained on CICIoMT2024 [114,131–133] run on network taps (detection scope; non-agentic baseline; edge topology) and flag suspect flows.”
SE-Enhanced ViT and BiLSTM-Based Intrusion Detection for Secure IIoT and IoMT Environments
Gueriani, A., Kheddar, H., Mazari, A. C., Sağıroğlu, Ş., & Ceran, O. (2025) · doi:10.1109/isctrkiye68593.2025.11224819 · Cited by 3
Metadata
- Authors
- Kavkas, N. C., & Yildiz, K.
- Affiliations
- Marmara University (TR)
- Marmara University,Computer Enginnering Faculty of Technology,Istanbul,Turkiye
- Venue
- 2025 13th International Symposium on Digital Forensics and Security (ISDFS)
- Publisher
- IEEE
- Published
- 2025-04-24
- Pages
- 1-5
- OpenAlex
- W4411207938
- Cited by
- 13
- References
- 0
- Citations by year
- 2026: 8 · 2025: 5
- FWCI
- 16.20
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International Symposium on Digital Forensics and Security (ISDFS) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
- Physical Sciences › Computer Science › Information Systems › Internet of Things and AI
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Keywords
- Internet of Medical Things, IoMT security, cyberattack detection, medical device security, deep neural network, long short-term memory, multi-class attack classification, patient privacy
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
