Identification of Darknet Markets' Bitcoin Addresses by Voting Per-Address Classification Results

Kota Kanemura, Kentaroh Toyoda, Tomoaki Ohtsuki

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Bitcoin is a decentralized digital currency whose transactions are recorded in a common ledger, so called blockchain. Due to the anonymity and lack of law enforcement, Bitcoin has been misused in darknet markets which deal with illegal products, such as drugs and weapons. Therefore from the security forensics aspect, it is demanded to establish an approach to identify newly emerged darknet markets' transactions and addresses. In this paper, we thoroughly analyze Bitcoin transactions and addresses related to darknet markets and propose a novel identification method of darknet markets' addresses. To improve the identification performance, we propose a voting based method which decides the labels of multiple addresses controlled by the same user based on the number of the majority label. Through the computer simulation with more than 200K Bitcoin addresses, it was shown that our voting based method outperforms the nonvoting based one in terms of precision, recal, and F1 score. We also found that DNM's addresses pay higher fees than others, which significantly improves the classification.

Original languageEnglish
Title of host publicationICBC 2019 - IEEE International Conference on Blockchain and Cryptocurrency
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages154-158
Number of pages5
ISBN (Electronic)9781728113289
DOIs
Publication statusPublished - 2019 May 1
Event1st IEEE International Conference on Blockchain and Cryptocurrency, ICBC 2019 - Seoul, Korea, Republic of
Duration: 2019 May 142019 May 17

Publication series

NameICBC 2019 - IEEE International Conference on Blockchain and Cryptocurrency

Conference

Conference1st IEEE International Conference on Blockchain and Cryptocurrency, ICBC 2019
CountryKorea, Republic of
CitySeoul
Period19/5/1419/5/17

Fingerprint

Labels
Law enforcement
Computer simulation
Voting
Electronic money

Keywords

  • Bitcoin
  • Classification
  • Forensic

ASJC Scopus subject areas

  • Business, Management and Accounting (miscellaneous)
  • Management of Technology and Innovation
  • Computer Networks and Communications
  • Information Systems and Management
  • Safety, Risk, Reliability and Quality

Cite this

Kanemura, K., Toyoda, K., & Ohtsuki, T. (2019). Identification of Darknet Markets' Bitcoin Addresses by Voting Per-Address Classification Results. In ICBC 2019 - IEEE International Conference on Blockchain and Cryptocurrency (pp. 154-158). [8751391] (ICBC 2019 - IEEE International Conference on Blockchain and Cryptocurrency). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BLOC.2019.8751391

Identification of Darknet Markets' Bitcoin Addresses by Voting Per-Address Classification Results. / Kanemura, Kota; Toyoda, Kentaroh; Ohtsuki, Tomoaki.

ICBC 2019 - IEEE International Conference on Blockchain and Cryptocurrency. Institute of Electrical and Electronics Engineers Inc., 2019. p. 154-158 8751391 (ICBC 2019 - IEEE International Conference on Blockchain and Cryptocurrency).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kanemura, K, Toyoda, K & Ohtsuki, T 2019, Identification of Darknet Markets' Bitcoin Addresses by Voting Per-Address Classification Results. in ICBC 2019 - IEEE International Conference on Blockchain and Cryptocurrency., 8751391, ICBC 2019 - IEEE International Conference on Blockchain and Cryptocurrency, Institute of Electrical and Electronics Engineers Inc., pp. 154-158, 1st IEEE International Conference on Blockchain and Cryptocurrency, ICBC 2019, Seoul, Korea, Republic of, 19/5/14. https://doi.org/10.1109/BLOC.2019.8751391
Kanemura K, Toyoda K, Ohtsuki T. Identification of Darknet Markets' Bitcoin Addresses by Voting Per-Address Classification Results. In ICBC 2019 - IEEE International Conference on Blockchain and Cryptocurrency. Institute of Electrical and Electronics Engineers Inc. 2019. p. 154-158. 8751391. (ICBC 2019 - IEEE International Conference on Blockchain and Cryptocurrency). https://doi.org/10.1109/BLOC.2019.8751391
Kanemura, Kota ; Toyoda, Kentaroh ; Ohtsuki, Tomoaki. / Identification of Darknet Markets' Bitcoin Addresses by Voting Per-Address Classification Results. ICBC 2019 - IEEE International Conference on Blockchain and Cryptocurrency. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 154-158 (ICBC 2019 - IEEE International Conference on Blockchain and Cryptocurrency).
@inproceedings{ff5a0ff316174611a9d7ae692690c815,
title = "Identification of Darknet Markets' Bitcoin Addresses by Voting Per-Address Classification Results",
abstract = "Bitcoin is a decentralized digital currency whose transactions are recorded in a common ledger, so called blockchain. Due to the anonymity and lack of law enforcement, Bitcoin has been misused in darknet markets which deal with illegal products, such as drugs and weapons. Therefore from the security forensics aspect, it is demanded to establish an approach to identify newly emerged darknet markets' transactions and addresses. In this paper, we thoroughly analyze Bitcoin transactions and addresses related to darknet markets and propose a novel identification method of darknet markets' addresses. To improve the identification performance, we propose a voting based method which decides the labels of multiple addresses controlled by the same user based on the number of the majority label. Through the computer simulation with more than 200K Bitcoin addresses, it was shown that our voting based method outperforms the nonvoting based one in terms of precision, recal, and F1 score. We also found that DNM's addresses pay higher fees than others, which significantly improves the classification.",
keywords = "Bitcoin, Classification, Forensic",
author = "Kota Kanemura and Kentaroh Toyoda and Tomoaki Ohtsuki",
year = "2019",
month = "5",
day = "1",
doi = "10.1109/BLOC.2019.8751391",
language = "English",
series = "ICBC 2019 - IEEE International Conference on Blockchain and Cryptocurrency",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "154--158",
booktitle = "ICBC 2019 - IEEE International Conference on Blockchain and Cryptocurrency",

}

TY - GEN

T1 - Identification of Darknet Markets' Bitcoin Addresses by Voting Per-Address Classification Results

AU - Kanemura, Kota

AU - Toyoda, Kentaroh

AU - Ohtsuki, Tomoaki

PY - 2019/5/1

Y1 - 2019/5/1

N2 - Bitcoin is a decentralized digital currency whose transactions are recorded in a common ledger, so called blockchain. Due to the anonymity and lack of law enforcement, Bitcoin has been misused in darknet markets which deal with illegal products, such as drugs and weapons. Therefore from the security forensics aspect, it is demanded to establish an approach to identify newly emerged darknet markets' transactions and addresses. In this paper, we thoroughly analyze Bitcoin transactions and addresses related to darknet markets and propose a novel identification method of darknet markets' addresses. To improve the identification performance, we propose a voting based method which decides the labels of multiple addresses controlled by the same user based on the number of the majority label. Through the computer simulation with more than 200K Bitcoin addresses, it was shown that our voting based method outperforms the nonvoting based one in terms of precision, recal, and F1 score. We also found that DNM's addresses pay higher fees than others, which significantly improves the classification.

AB - Bitcoin is a decentralized digital currency whose transactions are recorded in a common ledger, so called blockchain. Due to the anonymity and lack of law enforcement, Bitcoin has been misused in darknet markets which deal with illegal products, such as drugs and weapons. Therefore from the security forensics aspect, it is demanded to establish an approach to identify newly emerged darknet markets' transactions and addresses. In this paper, we thoroughly analyze Bitcoin transactions and addresses related to darknet markets and propose a novel identification method of darknet markets' addresses. To improve the identification performance, we propose a voting based method which decides the labels of multiple addresses controlled by the same user based on the number of the majority label. Through the computer simulation with more than 200K Bitcoin addresses, it was shown that our voting based method outperforms the nonvoting based one in terms of precision, recal, and F1 score. We also found that DNM's addresses pay higher fees than others, which significantly improves the classification.

KW - Bitcoin

KW - Classification

KW - Forensic

UR - http://www.scopus.com/inward/record.url?scp=85069209586&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069209586&partnerID=8YFLogxK

U2 - 10.1109/BLOC.2019.8751391

DO - 10.1109/BLOC.2019.8751391

M3 - Conference contribution

T3 - ICBC 2019 - IEEE International Conference on Blockchain and Cryptocurrency

SP - 154

EP - 158

BT - ICBC 2019 - IEEE International Conference on Blockchain and Cryptocurrency

PB - Institute of Electrical and Electronics Engineers Inc.

ER -