MétaCan
Menu
Back to cohort
Record W4401632402 · doi:10.22215/etd/2024-16076

Robust Defenses Against Adversarial Machine Learning in IoT Security

2024· dissertation· en· W4401632402 on OpenAlex
Olakunle Ibitoye

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

Venuenot available
Typedissertation
Languageen
FieldComputer Science
TopicAdversarial Robustness in Machine Learning
Canadian institutionsCarleton University
Fundersnot available
KeywordsAdversarial systemAdversarial machine learningContext (archaeology)Computer scienceArtificial intelligenceInternet of ThingsVulnerability (computing)Set (abstract data type)Machine learningComputer securityVulnerability assessmentData scienceGeography

Abstract

fetched live from OpenAlex

The cybersecurity of the Internet of Things (IoT) has been poised to benefit from Artificial Intelligence (AI).Advances such as AI-based Intrusion detection systems for IoT have shown promising results.However, these advances have been set back by the rise of Adversarial Samples.Adversarial Samples are specially crafted data samples that are designed to mislead an AI model into making a wrong prediction.When subjected to Adversarial Samples, AI models that have been optimally trained to make accurate predictions, will produce incorrect results.In this thesis document, we explore the reasons behind the vulnerability of AI models to Adversarial Samples.We also propose novel methods for addressing the challenge of Adversarial Samples in the specific context of cybersecurity applications for IoT.I would like to express my deepest appreciation to my PhD supervisors Dr. M. Omair Shafiq and Dr. Ashraf Matrawy for their guidance throughout the journey.

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.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Research integrity
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.716
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.001
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0020.001
Research integrity0.0010.003
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.014
GPT teacher head0.256
Teacher spread0.241 · 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