@inproceedings{przybyla-etal-2024-know,
title = "Know Thine Enemy: Adaptive Attacks on Misinformation Detection Using Reinforcement Learning",
author = "Przyby{\l}a, Piotr and
McGill, Euan and
Saggion, Horacio",
editor = "De Clercq, Orph{\'e}e and
Barriere, Valentin and
Barnes, Jeremy and
Klinger, Roman and
Sedoc, Jo{\~a}o and
Tafreshi, Shabnam",
booktitle = "Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, {\&} Social Media Analysis",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.wassa-1.11",
pages = "125--140",
abstract = "We present XARELLO: a generator of adversarial examples for testing the robustness of text classifiers based on reinforcement learning. Our solution is adaptive, it learns from previous successes and failures in order to better adjust to the vulnerabilities of the attacked model. This reflects the behaviour of a persistent and experienced attacker, which are common in the misinformation-spreading environment. We evaluate our approach using several victim classifiers and credibility-assessment tasks, showing it generates better-quality examples with less queries, and is especially effective against the modern LLMs. We also perform a qualitative analysis to understand the language patterns in the misinformation text that play a role in the attacks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="przybyla-etal-2024-know">
<titleInfo>
<title>Know Thine Enemy: Adaptive Attacks on Misinformation Detection Using Reinforcement Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Piotr</namePart>
<namePart type="family">Przybyła</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Euan</namePart>
<namePart type="family">McGill</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Horacio</namePart>
<namePart type="family">Saggion</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Orphée</namePart>
<namePart type="family">De Clercq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="family">Barriere</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeremy</namePart>
<namePart type="family">Barnes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Klinger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Sedoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shabnam</namePart>
<namePart type="family">Tafreshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present XARELLO: a generator of adversarial examples for testing the robustness of text classifiers based on reinforcement learning. Our solution is adaptive, it learns from previous successes and failures in order to better adjust to the vulnerabilities of the attacked model. This reflects the behaviour of a persistent and experienced attacker, which are common in the misinformation-spreading environment. We evaluate our approach using several victim classifiers and credibility-assessment tasks, showing it generates better-quality examples with less queries, and is especially effective against the modern LLMs. We also perform a qualitative analysis to understand the language patterns in the misinformation text that play a role in the attacks.</abstract>
<identifier type="citekey">przybyla-etal-2024-know</identifier>
<location>
<url>https://aclanthology.org/2024.wassa-1.11</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>125</start>
<end>140</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Know Thine Enemy: Adaptive Attacks on Misinformation Detection Using Reinforcement Learning
%A Przybyła, Piotr
%A McGill, Euan
%A Saggion, Horacio
%Y De Clercq, Orphée
%Y Barriere, Valentin
%Y Barnes, Jeremy
%Y Klinger, Roman
%Y Sedoc, João
%Y Tafreshi, Shabnam
%S Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F przybyla-etal-2024-know
%X We present XARELLO: a generator of adversarial examples for testing the robustness of text classifiers based on reinforcement learning. Our solution is adaptive, it learns from previous successes and failures in order to better adjust to the vulnerabilities of the attacked model. This reflects the behaviour of a persistent and experienced attacker, which are common in the misinformation-spreading environment. We evaluate our approach using several victim classifiers and credibility-assessment tasks, showing it generates better-quality examples with less queries, and is especially effective against the modern LLMs. We also perform a qualitative analysis to understand the language patterns in the misinformation text that play a role in the attacks.
%U https://aclanthology.org/2024.wassa-1.11
%P 125-140
Markdown (Informal)
[Know Thine Enemy: Adaptive Attacks on Misinformation Detection Using Reinforcement Learning](https://aclanthology.org/2024.wassa-1.11) (Przybyła et al., WASSA-WS 2024)
ACL