Research Article
Crypto Wallet Artifact Detection on Android Devices Using Advanced Machine Learning Techniques
@INPROCEEDINGS{10.1007/978-3-031-36574-4_7, author={Abhishek Bhattarai and Maryna Veksler and Hadi Sahin and Ahmet Kurt and Kemal Akkaya}, title={Crypto Wallet Artifact Detection on Android Devices Using Advanced Machine Learning Techniques}, proceedings={Digital Forensics and Cyber Crime. 13th EAI International Conference, ICDF2C 2022, Boston, MA, November 16-18, 2022, Proceedings}, proceedings_a={ICDF2C}, year={2023}, month={7}, keywords={Crypto wallet Cryptocurrency artifacts Triage Forensics Machine learning Android devices}, doi={10.1007/978-3-031-36574-4_7} }- Abhishek Bhattarai
Maryna Veksler
Hadi Sahin
Ahmet Kurt
Kemal Akkaya
Year: 2023
Crypto Wallet Artifact Detection on Android Devices Using Advanced Machine Learning Techniques
ICDF2C
Springer
DOI: 10.1007/978-3-031-36574-4_7
Abstract
As cryptocurrencies started to be used frequently as an alternative to regular cash and credit card payments, the wallet solutions/apps that facilitate their use also became increasingly popular.
This also intensified the involvement of these cryptowallet 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 the machines/devices and extract their artifacts. However, in many cases forensic investigators need to reach these file artifacts quickly with minimal manual intervention due to time and resource constraints. Therefore, in this paper, we present a comprehensive framework that incorporates various machine learning approaches to enable fast and automated extraction/triage of crypto related artifacts on Android devices. Specifically, our method can detect which cryptowallets exist on the device, their artifacts (i.e., database/log files), the crypto related pictures and web browsing data. For each type of data, we offer a specific machine learning technique such as Support Vector Machine, Logistic Regression and Neural Networks to detect and classify these files. Our evaluation results show very high accuracy detecting the file artifacts with respect to alternative tools.
