MétaCan
Menu
Back to cohort
Record W4378418350 · doi:10.18280/ria.370230

ConvNet Based Malicious URL Identification for Safer Use

2023· article· en· W4378418350 on OpenAlexvenueno aff
Vinod Sapkal, Praveen Gupta

Bibliographic record

VenueRevue d intelligence artificielle · 2023
Typearticle
Languageen
FieldComputer Science
TopicSpam and Phishing Detection
Canadian institutionsnot available
Fundersnot available
KeywordsSAFERIdentification (biology)Computer scienceComputer securityInternet privacyBiology

Abstract

fetched live from OpenAlex

A malicious URL or website is a type of threat that can affect the users' cybersecurity.It can host unsolicited content and lure users into clicking on links and downloading malware.It can also lead to the theft of private information and monetary losses.People must take the necessary steps to prevent these types of threats from happening promptly.Unfortunately, denylists are not capable of identifying new malicious content.Instead, they are mainly used to identify existing threats.Due to the increasing number of studies being conducted on the use of machine learning techniques, the general capabilities of these tools have been improved.The rise of the internet has made it an essential component of our lives.It allows us to exchange information and knowledge in a timelier manner.Unfortunately, identity fraud and identity theft are two of the most common forms of cybercrime.In both cases, the attackers' goal is to collect the users' personal data so they can commit fraud or deceit for financial gain.Phishing, drive-by exploits, and spam are some types of content commonly featured in malicious URLs.They are also designed to trick users into clicking on links and downloading malware.The vast majority of these scams are carried out through email, and they result in losses of billions of dollars.Systems that are capable of quickly identifying and preventing these types of crimes need to be developed, as well as have the ability to spot new malicious content.Blacklist methods have traditionally been used to detect these types of crimes.On the other hand, blacklists cannot identify newly produced harmful content.Due to the increasing number of studies being conducted on machine learning techniques to improve the detection of harmful web pages, the focus on this field has increased.This article presents an algorithm that can analyze and predict the likelihood of a link being good or bad.It is compared with other standard methods to analyze the performance of this method.

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)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesInsufficient payload (model declined to judge)
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 score0.968
Threshold uncertainty score0.999

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
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 integrity0.0000.000
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 head0.076
GPT teacher head0.292
Teacher spread0.217 · 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

Citations2
Published2023
Admission routes1
Has abstractyes

Explore more

Same venueRevue d intelligence artificielleSame topicSpam and Phishing DetectionFrench-language works237,207