VendorLink: An NLP approach for Identifying & Linking Vendor Migrants & Potential Aliases on Darknet Markets

Vageesh Saxena; Nils Rethmeier; Gijs Van Dijck; Gerasimos Spanakis

VendorLink: An NLP approach for Identifying & Linking Vendor Migrants & Potential Aliases on Darknet Markets

Vageesh Saxena, Nils Rethmeier, Gijs Van Dijck, Gerasimos Spanakis

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

1 Downloads (Pure)

Abstract

The anonymity on the Darknet allows vendors to stay undetected by using multiple vendor aliases or frequently migrating between markets. Consequently, illegal markets and their connections are challenging to uncover on the Darknet. To identify relationships between illegal markets and their vendors, we propose VendorLink, an NLP-based approach that examines writing patterns to verify, identify, and link unique vendor accounts across text advertisements (ads) on seven public Darknet markets. In contrast to existing literature, VendorLink utilizes the strength of supervised pre-training to perform closed-set vendor verification, open-set vendor identification, and low-resource market adaption tasks. Through VendorLink, we uncover (i) 15 migrants and 71 potential aliases in the Alphabay-Dreams-Silk dataset, (ii) 17 migrants and 3 potential aliases in the Valhalla-Berlusconi dataset, and (iii) 75 migrants and 10 potential aliases in the Traderoute-Agora dataset. Altogether, our approach can help Law Enforcement Agencies (LEA) make more informed decisions by verifying and identifying migrating vendors and their potential aliases on existing and Low-Resource (LR) emerging Darknet markets..

Original language	English
Title of host publication	ACL 2023 - 61st Conference of the the Association for Computational Linguistics, Proceedings of the Conference
Publisher	Association for Computational Linguistics (ACL)
Pages	8619-8639
Number of pages	21
Volume	1
ISBN (Electronic)	9781959429722
Publication status	Published - 1 Jan 2023
Event	61st Annual Meeting of the Association for Computational Linguistics, ACL 2023 - Toronto, Canada, Toronto, Canada Duration: 9 Jul 2023 → 14 Jul 2023 https://2023.aclweb.org/

Publication series

Series	Association for Computational Linguistics. Annual Meeting. Conference Proceedings
Volume	1
ISSN	0736-587X

Conference

Conference	61st Annual Meeting of the Association for Computational Linguistics, ACL 2023
Abbreviated title	ACL 2023
Country/Territory	Canada
City	Toronto
Period	9/07/23 → 14/07/23
Internet address	https://2023.aclweb.org/

Access to Document

Full TextFinal published version, 1.21 MBLicence: Taverne

Cite this

Saxena, Vageesh ; Rethmeier, Nils ; Van Dijck, Gijs et al. / VendorLink : An NLP approach for Identifying & Linking Vendor Migrants & Potential Aliases on Darknet Markets. ACL 2023 - 61st Conference of the the Association for Computational Linguistics, Proceedings of the Conference. Vol. 1 Association for Computational Linguistics (ACL), 2023. pp. 8619-8639 (Association for Computational Linguistics. Annual Meeting. Conference Proceedings, Vol. 1).

@inproceedings{35152c1c6ea04fc2a917955b41b08eb8,

title = "VendorLink: An NLP approach for Identifying & Linking Vendor Migrants & Potential Aliases on Darknet Markets",

abstract = "The anonymity on the Darknet allows vendors to stay undetected by using multiple vendor aliases or frequently migrating between markets. Consequently, illegal markets and their connections are challenging to uncover on the Darknet. To identify relationships between illegal markets and their vendors, we propose VendorLink, an NLP-based approach that examines writing patterns to verify, identify, and link unique vendor accounts across text advertisements (ads) on seven public Darknet markets. In contrast to existing literature, VendorLink utilizes the strength of supervised pre-training to perform closed-set vendor verification, open-set vendor identification, and low-resource market adaption tasks. Through VendorLink, we uncover (i) 15 migrants and 71 potential aliases in the Alphabay-Dreams-Silk dataset, (ii) 17 migrants and 3 potential aliases in the Valhalla-Berlusconi dataset, and (iii) 75 migrants and 10 potential aliases in the Traderoute-Agora dataset. Altogether, our approach can help Law Enforcement Agencies (LEA) make more informed decisions by verifying and identifying migrating vendors and their potential aliases on existing and Low-Resource (LR) emerging Darknet markets..",

author = "Vageesh Saxena and Nils Rethmeier and {Van Dijck}, Gijs and Gerasimos Spanakis",

note = "Funding Information: This research is supported by the Sector Plan Digital Legal Studies of the Dutch Ministry of Education, Culture, and Science and Cora4NLP project, funded by the German Federal Ministry of Education and Research (BMBF) under funding code 01IW20010. Finally, the experiments were made possible using the Data Science Research Infrastructure (DSRI) hosted at Maastricht University. Publisher Copyright: {\textcopyright} 2023 Association for Computational Linguistics.; 61st Annual Meeting of the Association for Computational Linguistics, ACL 2023, ACL 2023 ; Conference date: 09-07-2023 Through 14-07-2023",

year = "2023",

month = jan,

day = "1",

language = "English",

volume = "1",

series = "Association for Computational Linguistics. Annual Meeting. Conference Proceedings",

publisher = "Association for Computational Linguistics (ACL)",

pages = "8619--8639",

booktitle = "ACL 2023 - 61st Conference of the the Association for Computational Linguistics, Proceedings of the Conference",

address = "United States",

url = "https://2023.aclweb.org/",

}

Saxena, V, Rethmeier, N, Van Dijck, G & Spanakis, G 2023, VendorLink: An NLP approach for Identifying & Linking Vendor Migrants & Potential Aliases on Darknet Markets. in ACL 2023 - 61st Conference of the the Association for Computational Linguistics, Proceedings of the Conference. vol. 1, Association for Computational Linguistics (ACL), Association for Computational Linguistics. Annual Meeting. Conference Proceedings, vol. 1, pp. 8619-8639, 61st Annual Meeting of the Association for Computational Linguistics, ACL 2023, Toronto, Ontario, Canada, 9/07/23.

VendorLink: An NLP approach for Identifying & Linking Vendor Migrants & Potential Aliases on Darknet Markets. / Saxena, Vageesh; Rethmeier, Nils; Van Dijck, Gijs et al.
ACL 2023 - 61st Conference of the the Association for Computational Linguistics, Proceedings of the Conference. Vol. 1 Association for Computational Linguistics (ACL), 2023. p. 8619-8639 (Association for Computational Linguistics. Annual Meeting. Conference Proceedings, Vol. 1).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

TY - GEN

T1 - VendorLink

T2 - 61st Annual Meeting of the Association for Computational Linguistics, ACL 2023

AU - Saxena, Vageesh

AU - Rethmeier, Nils

AU - Van Dijck, Gijs

AU - Spanakis, Gerasimos

N1 - Funding Information: This research is supported by the Sector Plan Digital Legal Studies of the Dutch Ministry of Education, Culture, and Science and Cora4NLP project, funded by the German Federal Ministry of Education and Research (BMBF) under funding code 01IW20010. Finally, the experiments were made possible using the Data Science Research Infrastructure (DSRI) hosted at Maastricht University. Publisher Copyright: © 2023 Association for Computational Linguistics.

PY - 2023/1/1

Y1 - 2023/1/1

N2 - The anonymity on the Darknet allows vendors to stay undetected by using multiple vendor aliases or frequently migrating between markets. Consequently, illegal markets and their connections are challenging to uncover on the Darknet. To identify relationships between illegal markets and their vendors, we propose VendorLink, an NLP-based approach that examines writing patterns to verify, identify, and link unique vendor accounts across text advertisements (ads) on seven public Darknet markets. In contrast to existing literature, VendorLink utilizes the strength of supervised pre-training to perform closed-set vendor verification, open-set vendor identification, and low-resource market adaption tasks. Through VendorLink, we uncover (i) 15 migrants and 71 potential aliases in the Alphabay-Dreams-Silk dataset, (ii) 17 migrants and 3 potential aliases in the Valhalla-Berlusconi dataset, and (iii) 75 migrants and 10 potential aliases in the Traderoute-Agora dataset. Altogether, our approach can help Law Enforcement Agencies (LEA) make more informed decisions by verifying and identifying migrating vendors and their potential aliases on existing and Low-Resource (LR) emerging Darknet markets..

AB - The anonymity on the Darknet allows vendors to stay undetected by using multiple vendor aliases or frequently migrating between markets. Consequently, illegal markets and their connections are challenging to uncover on the Darknet. To identify relationships between illegal markets and their vendors, we propose VendorLink, an NLP-based approach that examines writing patterns to verify, identify, and link unique vendor accounts across text advertisements (ads) on seven public Darknet markets. In contrast to existing literature, VendorLink utilizes the strength of supervised pre-training to perform closed-set vendor verification, open-set vendor identification, and low-resource market adaption tasks. Through VendorLink, we uncover (i) 15 migrants and 71 potential aliases in the Alphabay-Dreams-Silk dataset, (ii) 17 migrants and 3 potential aliases in the Valhalla-Berlusconi dataset, and (iii) 75 migrants and 10 potential aliases in the Traderoute-Agora dataset. Altogether, our approach can help Law Enforcement Agencies (LEA) make more informed decisions by verifying and identifying migrating vendors and their potential aliases on existing and Low-Resource (LR) emerging Darknet markets..

M3 - Conference article in proceeding

VL - 1

T3 - Association for Computational Linguistics. Annual Meeting. Conference Proceedings

SP - 8619

EP - 8639

BT - ACL 2023 - 61st Conference of the the Association for Computational Linguistics, Proceedings of the Conference

PB - Association for Computational Linguistics (ACL)

Y2 - 9 July 2023 through 14 July 2023

ER -

Saxena V, Rethmeier N, Van Dijck G , Spanakis G. VendorLink: An NLP approach for Identifying & Linking Vendor Migrants & Potential Aliases on Darknet Markets. In ACL 2023 - 61st Conference of the the Association for Computational Linguistics, Proceedings of the Conference. Vol. 1. Association for Computational Linguistics (ACL). 2023. p. 8619-8639. (Association for Computational Linguistics. Annual Meeting. Conference Proceedings, Vol. 1).