A Framework for Anomaly Detection in IoT Networks Using Conditional Generative Adversarial Networks
Bibliographic record
Abstract
While anomaly detection and the related concept of intrusion detection are widely studied, detecting anomalies in new operating behavior in environments such as the Internet of Things (IoT) is an active field of research. Anomaly detection models trained on datasets that are likely imbalanced have poor results, but the ability of Generative Adversarial Networks (GANs) to emulate complex high-dimensional distributions seen in real-world data suggests that they may be effective for anomaly detection. This paper proposes a novel framework for detecting anomalies in IoT networks utilizing conditional GANs (cGANs) to build realistic distributions for a given feature set to overcome the issue of data imbalance. To this end, a single class cGAN (ocGAN) was utilized to learn the minority data class to balance the dataset. Then, the binary class cGAN (bcGAN) model generates augmented data for the binary balance dataset. The performance of the ocGAN and bcGAN models in binary and multiclass classification environments were evaluated using a feed-forward neural network (FFN) and tested on two network-based anomaly detection datasets and five IoT network-based anomaly detection datasets. The proposed models outperformed other anomaly detection models in the standard metrics of accuracy, precision, recall, and F1-score.
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 | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 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".