Privacy and security preservation of bitcoin digital currency transactions on mixing services using enhanced heuristic-aided optimal weighted features and hybrid deep learning network

Bitcoin (BTC) is a Peer-to-Peer (P2P) digital currency that facilitates transactions using pseudonymous identities. Mixing services improve the anonymity of transactions but are misused for illicit activities such as money laundering, raising security concerns in the BTC ecosystem. This research implements a hybridized deep learning approach for privacy preservation in BTC transactions. The required data are gathered from Elliptic Dataset and Ethereum Fraud Detection dataset, and these datasets are used for evaluation. The features are extracted from these datasets, followed by weighted attribute selection. The optimal feature selection and fine-tuning of the weights are implemented using the Improved Current Mussel Time-based Eurasian Oystercatcher Optimizer (ICMT-EOO) algorithm. The weighted attributes are classified using a Faster Regions-based Convolutional Neural Network with Dilated Bidirectional Long Short-Term Memory (FRCNN-DBi-LSTM). Experimental evaluation is performed using existing classifiers and optimization algorithms to demonstrate the efficiency of the approach. The proposed method achieves an accuracy of 95.2%, an F1-score of 92.98%, a recall of 95.21%, and a precision of 90.84%, respectively. The results confirm that the developed model achieves improved performance and enhanced security compared to existing methods.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2026-11-13
DOI
https://doi.org/10.1038/s41598-026-66962-8
Primary Topic
Blockchain Technology Applications and Security
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Privacy and security preservation of bitcoin digital currency transactions on mixing services using enhanced heuristic-aided optimal weighted features and hybrid deep learning network

S Ezhilmathi, Dr. Selvakumara Samy S
Scientific Reports
Blockchain Technology Applications and Security
article

Privacy and security preservation of bitcoin digital currency transactions on mixing services using enhanced heuristic-aided optimal weighted features and hybrid deep learning network

S Ezhilmathi, Dr. Selvakumara Samy S
article en

Abstract

Bitcoin (BTC) is a Peer-to-Peer (P2P) digital currency that facilitates transactions using pseudonymous identities. Mixing services improve the anonymity of transactions but are misused for illicit activities such as money laundering, raising security concerns in the BTC ecosystem. This research implements a hybridized deep learning approach for privacy preservation in BTC transactions. The required data are gathered from Elliptic Dataset and Ethereum Fraud Detection dataset, and these datasets are used for evaluation. The features are extracted from these datasets, followed by weighted attribute selection. The optimal feature selection and fine-tuning of the weights are implemented using the Improved Current Mussel Time-based Eurasian Oystercatcher Optimizer (ICMT-EOO) algorithm. The weighted attributes are classified using a Faster Regions-based Convolutional Neural Network with Dilated Bidirectional Long Short-Term Memory (FRCNN-DBi-LSTM). Experimental evaluation is performed using existing classifiers and optimization algorithms to demonstrate the efficiency of the approach. The proposed method achieves an accuracy of 95.2%, an F1-score of 92.98%, a recall of 95.21%, and a precision of 90.84%, respectively. The results confirm that the developed model achieves improved performance and enhanced security compared to existing methods.

Scientific Reports
SRM Institute of Science and Technology (IN)
Blockchain Technology Applications and Security
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon