Phishing detection in Blockchain Transactions with BEART and Deep CNN Model

Akshat Gaurav, Brij B. Gupta, Kwok Tai Chui

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Phishing attacks in blockchain transactions are a big problem for cryptocurrency exchanges. This paper presents a deep learning framework based on a Blockchain-Enhanced Attention Retention Transformer (BEART) with a deep CNN to find and classify phishing activities in blockchain transactions. To test our model, we used the Kaggle dataset. Our proposed framework also used a feature engineering technique to extract the most relevant features. Finally, our proposed framework gives a high accuracy of 96.24% in spotting phishing transactions.

Original languageEnglish
Title of host publicationProceedings of CONECCT 2024 - 10th IEEE International Conference on Electronics, Computing and Communication Technologies
ISBN (Electronic)9798350385922
DOIs
Publication statusPublished - 2024
Event10th IEEE International Conference on Electronics, Computing and Communication Technologies, CONECCT 2024 - Bangalore, India
Duration: 12 Jul 202414 Jul 2024

Publication series

NameProceedings of CONECCT 2024 - 10th IEEE International Conference on Electronics, Computing and Communication Technologies

Conference

Conference10th IEEE International Conference on Electronics, Computing and Communication Technologies, CONECCT 2024
Country/TerritoryIndia
CityBangalore
Period12/07/2414/07/24

Keywords

  • Blockchain Transactions
  • Deep Convolutional Neural Networks
  • Phishing Detection
  • SMOTE

Fingerprint

Dive into the research topics of 'Phishing detection in Blockchain Transactions with BEART and Deep CNN Model'. Together they form a unique fingerprint.

Cite this