@inproceedings{alperin-etal-2025-masks,
title = "Masks and Mimicry: Strategic Obfuscation and Impersonation Attacks on Authorship Verification",
author = "Alperin, Kenneth and
Leekha, Rohan and
Uchendu, Adaku and
Nguyen, Trang and
Medarametla, Srilakshmi and
Levya Capote, Carlos and
Aycock, Seth and
Dagli, Charlie",
editor = {H{\"a}m{\"a}l{\"a}inen, Mika and
{\"O}hman, Emily and
Bizzoni, Yuri and
Miyagawa, So and
Alnajjar, Khalid},
booktitle = "Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities",
month = may,
year = "2025",
address = "Albuquerque, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.nlp4dh-1.10/",
doi = "10.18653/v1/2025.nlp4dh-1.10",
pages = "102--116",
ISBN = "979-8-89176-234-3",
abstract = "The increasing use of Artificial Intelligence(AI) technologies, such as Large LanguageModels (LLMs) has led to nontrivial improvementsin various tasks, including accurate authorshipidentification of documents. However,while LLMs improve such defense techniques,they also simultaneously provide a vehicle formalicious actors to launch new attack vectors.To combat this security risk, we evaluate theadversarial robustness of authorship models(specifically an authorship verification model)to potent LLM-based attacks. These attacksinclude untargeted methods - authorship obfuscationand targeted methods - authorshipimpersonation. For both attacks, the objectiveis to mask or mimic the writing style of an authorwhile preserving the original texts' semantics,respectively. Thus, we perturb an accurateauthorship verification model, and achievemaximum attack success rates of 92{\%} and 78{\%}for both obfuscation and impersonation attacks,respectively."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alperin-etal-2025-masks">
<titleInfo>
<title>Masks and Mimicry: Strategic Obfuscation and Impersonation Attacks on Authorship Verification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kenneth</namePart>
<namePart type="family">Alperin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rohan</namePart>
<namePart type="family">Leekha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adaku</namePart>
<namePart type="family">Uchendu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trang</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Srilakshmi</namePart>
<namePart type="family">Medarametla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carlos</namePart>
<namePart type="family">Levya Capote</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seth</namePart>
<namePart type="family">Aycock</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Charlie</namePart>
<namePart type="family">Dagli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mika</namePart>
<namePart type="family">Hämäläinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="family">Öhman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuri</namePart>
<namePart type="family">Bizzoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">So</namePart>
<namePart type="family">Miyagawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Alnajjar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-234-3</identifier>
</relatedItem>
<abstract>The increasing use of Artificial Intelligence(AI) technologies, such as Large LanguageModels (LLMs) has led to nontrivial improvementsin various tasks, including accurate authorshipidentification of documents. However,while LLMs improve such defense techniques,they also simultaneously provide a vehicle formalicious actors to launch new attack vectors.To combat this security risk, we evaluate theadversarial robustness of authorship models(specifically an authorship verification model)to potent LLM-based attacks. These attacksinclude untargeted methods - authorship obfuscationand targeted methods - authorshipimpersonation. For both attacks, the objectiveis to mask or mimic the writing style of an authorwhile preserving the original texts’ semantics,respectively. Thus, we perturb an accurateauthorship verification model, and achievemaximum attack success rates of 92% and 78%for both obfuscation and impersonation attacks,respectively.</abstract>
<identifier type="citekey">alperin-etal-2025-masks</identifier>
<identifier type="doi">10.18653/v1/2025.nlp4dh-1.10</identifier>
<location>
<url>https://aclanthology.org/2025.nlp4dh-1.10/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>102</start>
<end>116</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Masks and Mimicry: Strategic Obfuscation and Impersonation Attacks on Authorship Verification
%A Alperin, Kenneth
%A Leekha, Rohan
%A Uchendu, Adaku
%A Nguyen, Trang
%A Medarametla, Srilakshmi
%A Levya Capote, Carlos
%A Aycock, Seth
%A Dagli, Charlie
%Y Hämäläinen, Mika
%Y Öhman, Emily
%Y Bizzoni, Yuri
%Y Miyagawa, So
%Y Alnajjar, Khalid
%S Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities
%D 2025
%8 May
%I Association for Computational Linguistics
%C Albuquerque, USA
%@ 979-8-89176-234-3
%F alperin-etal-2025-masks
%X The increasing use of Artificial Intelligence(AI) technologies, such as Large LanguageModels (LLMs) has led to nontrivial improvementsin various tasks, including accurate authorshipidentification of documents. However,while LLMs improve such defense techniques,they also simultaneously provide a vehicle formalicious actors to launch new attack vectors.To combat this security risk, we evaluate theadversarial robustness of authorship models(specifically an authorship verification model)to potent LLM-based attacks. These attacksinclude untargeted methods - authorship obfuscationand targeted methods - authorshipimpersonation. For both attacks, the objectiveis to mask or mimic the writing style of an authorwhile preserving the original texts’ semantics,respectively. Thus, we perturb an accurateauthorship verification model, and achievemaximum attack success rates of 92% and 78%for both obfuscation and impersonation attacks,respectively.
%R 10.18653/v1/2025.nlp4dh-1.10
%U https://aclanthology.org/2025.nlp4dh-1.10/
%U https://doi.org/10.18653/v1/2025.nlp4dh-1.10
%P 102-116
Markdown (Informal)
[Masks and Mimicry: Strategic Obfuscation and Impersonation Attacks on Authorship Verification](https://aclanthology.org/2025.nlp4dh-1.10/) (Alperin et al., NLP4DH 2025)
ACL
- Kenneth Alperin, Rohan Leekha, Adaku Uchendu, Trang Nguyen, Srilakshmi Medarametla, Carlos Levya Capote, Seth Aycock, and Charlie Dagli. 2025. Masks and Mimicry: Strategic Obfuscation and Impersonation Attacks on Authorship Verification. In Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities, pages 102–116, Albuquerque, USA. Association for Computational Linguistics.