Rogue device discrimination in ZigBee networks using wavelet transform and autoencoders
Bibliographic record
Abstract
In modern wireless systems such as ZigBee, sensitive information which is produced by the network is transmitted through different wired or wireless nodes. Providing the requisites of communication between diverse communication system types, such as mobiles, laptops, and desktop computers, does increase the risk of being attacked by outside nodes. Malicious (or unintentional) threats, such as trying to obtain unauthorized accessibility to the network, increase the requirements of data security against the rogue devices trying to tamper with the identity of authorized devices. In such manner, focusing on Radio Frequency Distinct Native Attributes (RF-DNA) of features extracted from physical layer responses (referred to as preambles) of ZigBee devices, a dataset of distinguishable features of all devices can be produced which can be exploited for the detection and rejection of spoofing/rogue devices. Through this procedure, distinction of devices manufactured by the different/same producer(s) can be realized resulting in an improvement of classification system accuracy. The two most challenging problems in initiating RF-DNA are (1) the mechanism of features extraction in the generation of a dataset in the most effective way for model classification and (2) the design of an efficient model for device discrimination of spoofing/rogue devices. In this paper, we analyze the physical layer features of ZigBee devices and present methods based on deep learning algorithms to achieve high classification accuracy, based on wavelet decomposition and on the autoencoder representation of the original dataset.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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 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".