MétaCan
Menu
Back to cohort

Adversarial Vulnerabilities in Machine Learning: Differential Analysis of Gradient and XGBoost-Based Attack Mechanisms

2025· article· W7131300647 on OpenAlexaff
Monali Parikh, Rashmika N Baria, Vatsal M Rakholiya, Shivang Parekh, Parag Nagrecha

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicAdversarial Robustness in Machine Learning
Canadian institutionsSeneca Polytechnic
Fundersnot available
KeywordsAdversarial systemInterpretabilityExploitAdversarial machine learningRobustness (evolution)Key (lock)CompromiseThreat model

Abstract

fetched live from OpenAlex

Adversarial attacks exploit vulnerabilities in machine learning (ML) and deep learning (DL) models by introducing subtle perturbations to input data, leading to significant misclassifications. This review provides a comprehensive analysis of gradient-based and XGBoost-based adversarial attacks and their effects on model robustness. It examines how gradient manipulation and boosted decision frameworks compromise feature representations and prediction boundaries, emphasizing their implications in critical ML applications. The paper systematically differentiates between classical adversarial, gradient-driven, and XGBoost-driven attack paradigms, highlighting their methodological variations and computational complexity. A detailed comparison through differential analysis reveals key patterns in attack susceptibility across model types and datasets. Furthermore, existing research contributions and limitations are evaluated to identify gaps in current defense mechanisms. The study concludes by outlining future research directions focused on explainable defense strategies, adversarial training optimization, and robustness evaluation frameworks aimed at enhancing the security and interpretability of modern AI systems.

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 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)0.002
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
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 score0.809
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.001
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0020.001
Bibliometrics0.0030.005
Science and technology studies0.0000.001
Scholarly communication0.0000.000
Open science0.0010.001
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0010.000

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 head0.272
Teacher spread0.258 · 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 teacher head, not a consensus.

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 topicAdversarial Robustness in Machine LearningFrench-language works237,207