Cryptocurrency forensics automation: a deep learning and NLP-based approach for mobile platforms

Abstract As cryptocurrencies have become increasingly used as an alternative to regular cash and credit card payments, the wallet solutions/apps that facilitate their use have also become increasingly popular. This has also intensified the involvement of these crypto wallet apps in criminal activiti...

Full description

Saved in:
Bibliographic Details
Main Authors: Abhishek Bhattarai, Abdulhadi Sahin, Maryna Veksler, Ahmet Kurt, Devrim Aras, Carlos Imery, Kemal Akkaya
Format: Article
Language:English
Published: Springer 2025-06-01
Series:Discover Computing
Subjects:
Online Access:https://doi.org/10.1007/s10791-025-09595-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849329419612585984
author Abhishek Bhattarai
Abdulhadi Sahin
Maryna Veksler
Ahmet Kurt
Devrim Aras
Carlos Imery
Kemal Akkaya
author_facet Abhishek Bhattarai
Abdulhadi Sahin
Maryna Veksler
Ahmet Kurt
Devrim Aras
Carlos Imery
Kemal Akkaya
author_sort Abhishek Bhattarai
collection DOAJ
description Abstract As cryptocurrencies have become increasingly used as an alternative to regular cash and credit card payments, the wallet solutions/apps that facilitate their use have also become increasingly popular. This has also intensified the involvement of these crypto wallet apps in criminal activities such as ransom requests, money laundering, and transactions on dark markets. From a digital forensics point of view, it is crucial to have tools and reliable approaches to detect these wallets on devices and extract their artifacts quickly with greater efficiency. However, with current research and trends, forensic investigators still need to manually extract these file artifacts, which delays the time-sensitive investigation findings. As mobile devices increasingly facilitate cryptocurrency transactions, there emerges a critical gap and need for automated evidence extraction to detect crucial artifacts preventing illicit activities. Therefore, in this paper, we present a comprehensive framework that incorporates various machine learning (ML), image processing, and natural language processing (NLP) approaches to enable fast and automated extraction/triage of crypto-related artifacts from Android and iOS devices. Specifically, our method can automatically detect which crypto wallet exists on the device, their artifacts (i.e., database/log files), along with the crypto-related images, web browsing data, and SMS conversations. For each type of data, we offer a specific ML technique, such as Support Vector Machine, Logistic Regression, and Neural Networks, to detect and classify these files. Our evaluation results show very high accuracy compared to alternative tools: our wallet classification model achieves 91% recall, crypto-related image classification achieves 75% accuracy, browsing data achieves 100% accuracy, and the SMS message model achieves 85% accuracy.
format Article
id doaj-art-a8d5f6fbc7de43a6a3d9acb7a117d7b1
institution Kabale University
issn 2948-2992
language English
publishDate 2025-06-01
publisher Springer
record_format Article
series Discover Computing
spelling doaj-art-a8d5f6fbc7de43a6a3d9acb7a117d7b12025-08-20T03:47:16ZengSpringerDiscover Computing2948-29922025-06-0128112710.1007/s10791-025-09595-1Cryptocurrency forensics automation: a deep learning and NLP-based approach for mobile platformsAbhishek Bhattarai0Abdulhadi Sahin1Maryna Veksler2Ahmet Kurt3Devrim Aras4Carlos Imery5Kemal Akkaya6Advanced Wireless and Security Lab, Florida International UniversityAdvanced Wireless and Security Lab, Florida International UniversityAdvanced Wireless and Security Lab, Florida International UniversityDepartment of Computer Science and Information Systems, East Texas A&M UniversityAdvanced Wireless and Security Lab, Florida International UniversityAdvanced Wireless and Security Lab, Florida International UniversityAdvanced Wireless and Security Lab, Florida International UniversityAbstract As cryptocurrencies have become increasingly used as an alternative to regular cash and credit card payments, the wallet solutions/apps that facilitate their use have also become increasingly popular. This has also intensified the involvement of these crypto wallet apps in criminal activities such as ransom requests, money laundering, and transactions on dark markets. From a digital forensics point of view, it is crucial to have tools and reliable approaches to detect these wallets on devices and extract their artifacts quickly with greater efficiency. However, with current research and trends, forensic investigators still need to manually extract these file artifacts, which delays the time-sensitive investigation findings. As mobile devices increasingly facilitate cryptocurrency transactions, there emerges a critical gap and need for automated evidence extraction to detect crucial artifacts preventing illicit activities. Therefore, in this paper, we present a comprehensive framework that incorporates various machine learning (ML), image processing, and natural language processing (NLP) approaches to enable fast and automated extraction/triage of crypto-related artifacts from Android and iOS devices. Specifically, our method can automatically detect which crypto wallet exists on the device, their artifacts (i.e., database/log files), along with the crypto-related images, web browsing data, and SMS conversations. For each type of data, we offer a specific ML technique, such as Support Vector Machine, Logistic Regression, and Neural Networks, to detect and classify these files. Our evaluation results show very high accuracy compared to alternative tools: our wallet classification model achieves 91% recall, crypto-related image classification achieves 75% accuracy, browsing data achieves 100% accuracy, and the SMS message model achieves 85% accuracy.https://doi.org/10.1007/s10791-025-09595-1CryptowalletCryptocurrency artifactsCryptocurrency forensicsCryptocurrency crime investigationMobile forensicsForensics automation
spellingShingle Abhishek Bhattarai
Abdulhadi Sahin
Maryna Veksler
Ahmet Kurt
Devrim Aras
Carlos Imery
Kemal Akkaya
Cryptocurrency forensics automation: a deep learning and NLP-based approach for mobile platforms
Discover Computing
Cryptowallet
Cryptocurrency artifacts
Cryptocurrency forensics
Cryptocurrency crime investigation
Mobile forensics
Forensics automation
title Cryptocurrency forensics automation: a deep learning and NLP-based approach for mobile platforms
title_full Cryptocurrency forensics automation: a deep learning and NLP-based approach for mobile platforms
title_fullStr Cryptocurrency forensics automation: a deep learning and NLP-based approach for mobile platforms
title_full_unstemmed Cryptocurrency forensics automation: a deep learning and NLP-based approach for mobile platforms
title_short Cryptocurrency forensics automation: a deep learning and NLP-based approach for mobile platforms
title_sort cryptocurrency forensics automation a deep learning and nlp based approach for mobile platforms
topic Cryptowallet
Cryptocurrency artifacts
Cryptocurrency forensics
Cryptocurrency crime investigation
Mobile forensics
Forensics automation
url https://doi.org/10.1007/s10791-025-09595-1
work_keys_str_mv AT abhishekbhattarai cryptocurrencyforensicsautomationadeeplearningandnlpbasedapproachformobileplatforms
AT abdulhadisahin cryptocurrencyforensicsautomationadeeplearningandnlpbasedapproachformobileplatforms
AT marynaveksler cryptocurrencyforensicsautomationadeeplearningandnlpbasedapproachformobileplatforms
AT ahmetkurt cryptocurrencyforensicsautomationadeeplearningandnlpbasedapproachformobileplatforms
AT devrimaras cryptocurrencyforensicsautomationadeeplearningandnlpbasedapproachformobileplatforms
AT carlosimery cryptocurrencyforensicsautomationadeeplearningandnlpbasedapproachformobileplatforms
AT kemalakkaya cryptocurrencyforensicsautomationadeeplearningandnlpbasedapproachformobileplatforms