Temporal Partitioned Federated Learning for IoT Intrusion Detection Systems
Bibliographic record
Abstract
Machine learning-based intrusion detection systems (IDSs) serve as a defense-in-depth layer for Internet of Things (IoT) networks by detecting potential intrusions within IoT traffic. However, resource-constrained IoT devices impose sig-nificant challenges in developing effective IDSs. Recently, fed-erated learning (FL) has emerged as a promising solution for training detection models on distributed IoT devices without compromising resource limitations resulting in the introduction of FL-based IDSs. To this end, this paper introduces a novel approach to enhance the effectiveness of current FL-based IoT IDSs while utilizing the same resources. The proposed system partitions the FL rounds between IoT device groups, allowing each group to update the FL detection model during its time partition. Hence, by implementing this temporal partitioning, multiple detection models are updated within one FL round using the same IoT resources. The main design goals of the proposed approach are to improve detection accuracy and convergence time compared to the traditional approach. For this purpose, the proposed approach is evaluated and compared to the traditional approach using five intrusion scenarios on IoT traffic obtained from the Edge-IIoTset dataset. The results demonstrate that the proposed temporal partitioned FL-based IoT IDS outperforms the traditional system by achieving higher detection accuracy and faster convergence time. Furthermore, the proposed approach achieves the required detection accuracy in fewer FL rounds, which can, in principle, save more IoT resources.
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 | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 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".