MétaCan
Menu
Back to cohort
Record W3204617018 · doi:10.1145/3423153

A Novel Real-time Anti-spam Framework

2021· article· en· W3204617018 on OpenAlex

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

VenueACM Transactions on Internet Technology · 2021
Typearticle
Languageen
FieldComputer Science
TopicSpam and Phishing Detection
Canadian institutionsCarleton University
Fundersnot available
KeywordsComputer scienceConvolutional neural networkClassifier (UML)Precision and recallRecallMachine learningLong short term memoryArtificial intelligenceData miningRecurrent neural networkArtificial neural network

Abstract

fetched live from OpenAlex

As one of the most pervasive current modes of communication, email needs to be fast and reliable. However, spammers and attackers use it as a primary channel to conduct illegal activities. Although many approaches have been developed and evaluated for spam detection, they do not provide sufficient accuracy. This deficiency results in significant economic losses for organizations. In this article, we first propose a framework for creating novel spam filters using Keras to combine a Convolutional Neural Network (CNN) with Long Short-Term Memory (LSTM) classification models. We then use this framework to introduce a specific solution applicable to realistic scenarios involving dynamic incoming email data in real-time. This solution takes the form of a real-time content-based spam classifier. We evaluate its performance concerning accuracy, precision, recall, false-positive, and false-negative rates. Our experimental results show that our approach can significantly outperform existing solutions for real-time spam detection.

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)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.781
Threshold uncertainty score0.710

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.001

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 head0.014
GPT teacher head0.250
Teacher spread0.235 · 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