MétaCan
Menu
Back to cohort

Advanced Modeling of AI, Machine Learning, and Deep Learning Approaches for Phishing Attack Detection on the Web

2025· article· W7124966204 on OpenAlexaff
Ashvin J. Ade, Pritish A. Tijare

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicSpam and Phishing Detection
Canadian institutionsArtificial Intelligence in Medicine (Canada)
Fundersnot available
KeywordsAdversarial systemRelevance (law)CyberspacePhishingDeep learningSoftware deploymentThe InternetConsistency (knowledge bases)

Abstract

fetched live from OpenAlex

Traditional phishing attacks take precedence among heavily used threats against internet security, capitalizing on user-perceived vulnerabilities, system architecture, and digital communication channels. In this study, we provide an elaborate statistical analytical review of some recent research works utilizing Machine Learning (ML), Deep Learning (DL), and Artificial Intelligence (AI) techniques for phishing detection. The review covered qualitative methodology synthesis and quantitative bench marking against performance indicators: accuracy, reliability, computational overhead, efficiency, and complexity. Each method was analyzed concerning its architectural framework, application situation, model fine-tuning, and experiment design. Apart from the popular measures, memory and time complexity are unique to our study, making it suited to aid in decisionmaking real-world deployment. To achieve internal consistency and facilitate comparison, both stated values and expert-derived values were brought into a singular tabular framework to be presented herein. The results show consistently better predictive and stable performance of hybrid optimization-DL models and transformers-based detectors against standalone variants of ML. Nonetheless, interpret ability of models, resource requirements, and adversarial resistivity still remain problematic. This work hence ameliorates against the most critical disadvantages of prior surveys by combining empiric with sound commentary and outlining actionable avenues for furthering next research efforts. It encompasses both a well-defined taxonomy and a performancecentered road map for all researchers and practitioners searching for unique, scalable, and ethical solutions toward phishing detection process. The statistical lucidity and deployment relevance of this work raise it from an ordinary review to a decision support system for advanced strategies in cyberspace defense scenarios.

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)0.003
metaresearch head score (Gemma)0.007
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: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.007
Threshold uncertainty score0.016

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0030.007
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0020.002
Science and technology studies0.0000.001
Scholarly communication0.0020.003
Open science0.0010.001
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0020.000

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 head0.042
GPT teacher head0.268
Teacher spread0.226 · 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 topicSpam and Phishing DetectionFrench-language works237,207