MétaCan
Menu
Back to cohort
Record W7116710490 · doi:10.1109/tim.2025.3643032

Passive IoT Device Fingerprinting With Polynomial Curve Fitting and Siamese Neural Networks

2025· article· W7116710490 on OpenAlexaff
Olivier Cabana, Mourad Debbabi, El-Nasser S. Youssef, Marthe Kassouf

Bibliographic record

VenueIEEE Transactions on Instrumentation and Measurement · 2025
Typearticle
Language
FieldComputer Science
TopicInternet Traffic Analysis and Secure E-voting
Canadian institutionsHydro-QuébecConcordia University
Fundersnot available
KeywordsInternet of ThingsArtificial neural networkPolynomialSet (abstract data type)Anomaly detectionSoftware deploymentCurve fitting

Abstract

fetched live from OpenAlex

The Internet of Things (IoT) provides significant utility but also comes with several security risks. Device fingerprinting enables visibility, authentication, and anomaly detection which are essential to IoT network security. We propose a passive fingerprinting method that encodes network traffic using polynomial curve fitting and trains a Siamese Neural Network (SNN) to generate device embeddings. Finally, we estimate the geometric median of the set of embeddings for each device and use it for the device representation. Our approach can thus identify traffic from existing IoT devices in the network, and can classify new devices being introduced to the network. Evaluated on three public and one private dataset, our approach achieves 98% average accuracy. The proposed method operates without assumptions about the underlying network, device types, or protocols, making it suitable for real-world deployment across diverse IoT environments.

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 imitation

Not 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.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.003
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.005
Threshold uncertainty score0.009

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.003
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.002
Science and technology studies0.0000.001
Scholarly communication0.0010.002
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0010.001

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.

Opus teacher head0.020
GPT teacher head0.245
Teacher spread0.225 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

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".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueIEEE Transactions on Instrumentation and MeasurementSame topicInternet Traffic Analysis and Secure E-votingFrench-language works237,207