Attention-Based Interpretable Semi-Supervised Federated Learning for Intrusion Detection in IoT Wireless Networks
Bibliographic record
Abstract
Intrusion detection is a crucial task to ensure the security of the Internet of Things (IoT) wireless networks. While different Machine Learning (ML) methods have been leveraged to detect network intrusion, they often require data from multiple devices to be collected and stored on a central server to train underlying ML models, raising privacy concerns. Federated Learning (FL) can preserve data privacy where local devices can iteratively update the model parameters trained by using their own local datasets and send them to a server for model ag-gregation. Moreover, most existing ML-based intrusion detection designs are based on supervised ML using labeled data, which may not be available or time-consuming to build. Therefore, semi-supervised learning methods that effectively utilize both labeled and unlabeled data would be very desirable and necessary. This paper proposes a semi-supervised FL method for intrusion detection in IoT networks. Specifically, our proposed framework leverages the attention-based architecture called TabNet to selec-tively focus on important features of network flow and we propose a crucial data preparation procedure before training the ML model using the FL approach. We conduct extensive numerical studies to demonstrate the effectiveness of our approach and compare its performance to other baselines. We also present empirical evidence to support the interpretability of our method. We also show that the proposed data pre-processing procedure indeed greatly enhances the intrusion detection performance. <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup>
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".