Advancing IoMT Security with Privacy-Preserving Federated Learning Techniques
Bibliographic record
Abstract
The rapid expansion of the Internet of Medical Things (IoM$T$) has improved the healthcare system by enabling real-time patient monitoring, diagnosis, and treatment through connected devices. However, these advancements introduce secu-rity risks, making Intrusion Detection Systems (IDS) essential for detecting and mitigating cyber threats. Traditional IDS solutions rely on centralized machine learning (ML) models, which require transferring sensitive patient data to a central server. This raises privacy concerns and poses challenges in handling large-scale data efficiently. To address these issues, this paper proposes a novel Federated Learning (FL) framework that enhances IoMT security while preserving data privacy. Our approach integrates Local Differential Privacy (LDP) to protect individual data points and employs a Neural Oblivious Decision Ensembles (NODE) model, optimized for tabular IoMT data. We utilize Federated Averaging (FedAvg) as the primary aggregation algorithm and benchmark it against FedAvgM, FedAdam, and FedAdagrad using the Flower FL framework. The framework was evaluated on state-of-the-art datasets for real-world IoMT attack scenarios: the IoMT-TrafficData dataset was used for training, and the CICIoMT2024 dataset was used for inference, facilitating the multiclass classification of various attack types. Our results indicate that our approach achieves high efficiency and strong generalization capabilities across diverse IoM$T$attack scenarios.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.002 | 0.004 |
| Open science | 0.002 | 0.004 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".