Device-Specific Anomaly Detection Models for IoT Systems
Bibliographic record
Abstract
The Internet of Things (IoT) has transformed home automation, industry, and agriculture, yet security remains a major challenge. IoT systems comprise a wide range of devices generating vast and heterogeneous data. This paper investigates device-specific and device-type-specific anomaly detection models, highlighting the potential of leveraging unique traffic patterns from heterogeneous IoT devices. These models are compared to a single model trained on data from all devices, using eight different supervised and unsupervised One-Class Classifier (OCC) methods on two IoT-collected datasets.Typically, real-world IoT devices generate normal traffic prior to any attack or intrusion. With an abundance of normal traffic and no labelled attack data, unsupervised learning becomes a suitable approach. The findings of this paper show that when using unsupervised methods, device-specific and device-type-specific models outperform single models, particularly when the data is dominated by one class. In this context, device/device-type models can be more effective for real-time anomaly detection by identifying attacks as deviations from the normal profiles established for each device or device type.
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 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 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".