Detecting Phishing URLs With Word Embedding and Deep Learning

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F62690094%3A18450%2F23%3A50020570" target="_blank" >RIV/62690094:18450/23:50020570 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.4018/978-1-6684-7684-0.ch011" target="_blank" >http://dx.doi.org/10.4018/978-1-6684-7684-0.ch011</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.4018/978-1-6684-7684-0.ch011" target="_blank" >10.4018/978-1-6684-7684-0.ch011</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Detecting Phishing URLs With Word Embedding and Deep Learning

Popis výsledku v původním jazyce

learning in the phishing detection domain. However, there needs to be more research on word embeddingand deep learning for malicious URL classification. Inspired to solve this problem, this chapter aims toexamine the application of word embedding and deep learning in extracting features from website URLs.To achieve this, several word embedding techniques, such as Keras, Word2Vec, GloVe, and FastText,were used to learn feature representations of webpage URLs. The obtained feature vectors were fed intoa deep-learning model based on CNN-BiGRU for extraction and classification. Two different datasetswere used to conduct numerous experiments, while various metrics were utilized to evaluate the phishingdetection model’s performance. The obtained findings indicated that when combined with deep learning,Keras outperformed other text embedding methods and achieved the best results across all evaluationmetrics on both datasets.

Název v anglickém jazyce

Detecting Phishing URLs With Word Embedding and Deep Learning

Popis výsledku anglicky

learning in the phishing detection domain. However, there needs to be more research on word embeddingand deep learning for malicious URL classification. Inspired to solve this problem, this chapter aims toexamine the application of word embedding and deep learning in extracting features from website URLs.To achieve this, several word embedding techniques, such as Keras, Word2Vec, GloVe, and FastText,were used to learn feature representations of webpage URLs. The obtained feature vectors were fed intoa deep-learning model based on CNN-BiGRU for extraction and classification. Two different datasetswere used to conduct numerous experiments, while various metrics were utilized to evaluate the phishingdetection model’s performance. The obtained findings indicated that when combined with deep learning,Keras outperformed other text embedding methods and achieved the best results across all evaluationmetrics on both datasets.

Druh

C - Kapitola v odborné knize

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název knihy nebo sborníku

Perspectives and Considerations on the Evolution of Smart Systems

ISBN

978-1-66847-684-0

Počet stran výsledku

24

Strana od-do

296-319

Počet stran knihy

419

Název nakladatele

IGI Global

Místo vydání

Hershey

Kód UT WoS kapitoly

—