Delay and Energy-Efficient Asynchronous Federated Learning for Intrusion Detection in Heterogeneous Industrial Internet of Things
Bibliographic record
Abstract
Federated learning (FL) is a promising solution to overcome data island and privacy issues in intrusion detection systems (IDSs) for the Industrial Internet of Things (IIoT). However, the heterogeneity of various IIoT devices poses formidable challenges to FL-based intrusion detection, especially the training cost relating to delay and energy consumption. In this article, we propose a delay and energy-efficient asynchronous FL (AFL) framework for intrusion detection (DEAFL-ID) in heterogeneous IIoT. Specifically, we address the shortcomings of low efficiency and high energy consumption in existing FL-based solutions involving all idle IIoT devices. To do so, we formulate an AFL-based optimal device selection problem which aims to select high-quality training devices in advance by exploring the device advantages in detection accuracy, delay reduction, and energy saving. Subsequently, a deep Q-network (DQN)-based learning algorithm is developed to quickly solve the above high-dimensional problem. In addition, to further improve the detection performance, we build a hybrid sampling-assisted convolutional neural network (CNN)-based IDS model, which can eliminate the imbalance of IIoT data and enable the selected devices to fully extract data features. Through simulations, we demonstrate that DEAFL-ID achieves a significant improvement in training cost and detection performance compared with existing IDS schemes.
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 | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".